SlideShare ist ein Scribd-Unternehmen logo
1 von 30
Downloaden Sie, um offline zu lesen
Enhancing intelligent
agents with episodic
memories
Dan Tecuci
dan.tecuci@us.ibm.com
Cognitive Systems Institute Weekly Meeting
Sep 8, 2016
2
Outline
• Motivation
– Human Memory
– Why is episodic memory needed in a cognitive
system?
• Approach
– Generic Episodic Memory Module
– Requirements
– A proposed implementation
• Evaluation
• Conclusions & Discussion
WHY DO WE NEED MEMORY?
“Those who cannot remember the past are condemned to repeat it.”
George Santyana
• Remembering is an essential characteristic of intelligence
• Humans can
– recall their past experience
– Use memories to
– solve similar problems
– avoid unwanted behavior
– recognize plans - infer other people’s goals
– remember own goals and track progress
• Memory and intelligence go hand in hand
Why it’s important to remember the past
4
• Experience
– important knowledge source
– mostly unused in current systems
• Importance of experience grows with
– Complexity of task
– Life-expectancy of system
• Eager approach (generalize & discard) – machine learning
– Assumes all value can be extracted up-front
• Lazy approach (store for now, use later)
– Defers (part of) learning till later
The Role of Memory in a Cognitive System
5
6
Benefits of Using Stored Memories
• Memory enables a system to:
–improve performance
– solve problem faster by adapting previous solutions
–improve competence
– informed search
–perform additional tasks
–avoid and detect failures
– monitor long-term goals
– reflect on past
7
Human Memory - Episodic vs. Semantic
• Differences
– concrete vs. abstract
– dated vs. timeless
– personal vs. general
• Similarities
– knowledge is acquired through senses
– automatic retention
– retrieval triggered by stimuli, automatic
8
Episodic Memory Functions
• Encoding
– activation (when to store an episode)
– salient feature selection (what to sore in an episode)
– cue selection (what features to use as cues)
• Storage
– how to maintain an episode in memory (forgetting)
• Retrieval
– cue construction
– matching
– recall
– recollective experience
A GENERIC EPISODIC
MEMORY MODULE
• Characteristics:
– Generic
– Same memory - different apps
– Can be used for various tasks and domains
– Separate from application
– Interface through API
– Store complex experience (e.g. temporal, graph-based)
• Memory function:
– Return most relevant prior episodes
• Advantages:
– focus on memory organization
– reduce complexity of overall system
PROPOSAL: Generic Memory Module
10
• Accuracy in retrieval - retrieve memories relevant to
the situation at hand
• Scalability - accommodate a large number of
episodes without a significant decrease in
performance
• Efficiency - efficient storage and retrieval (both in
space and time)
• Content addressability - memories should be
addressable by their content
• Flexible matching - recognize prior situations even if
they only partially match the current one
General Memory Requirements
11
• Conceptual representation for generic events
• Domain-independent storage/retrieval algorithms
• Flexible interface
Challenges
12
• Episode
– unit of storage
– capture a complex event, with temporal extent.
– represented as Conceptual graphs (sets of S-P-O triples)
– Use ontology for concept representation
• Divide episodes into three dimensions
– context = setting of episode
– contents = ordered set of events
– outcome = evaluation of episode’s effects
• What constitutes an episode – application
Episode Representation
13
14
Planning Episode Example
Context: “move all perl scripts to the linux folder”
Contents:
sh> find -name linux
./code/linux
sh> find -name *.pl
./code/accessor.pl
./code/constructor.pl
./code/gang/dwarf/aml.pl
sh> mv ./bin/gang/set/convert.pl
./code/accessor.pl
./code/constructor.pl
./code/gang/dwarf/aml.pl
./code/linux
Outcome: “Success”
15
Using Stored Episodes
• Episodes should be multifunctional
– Same episode can be used for different purposes
• E.g. Planning Episode = [plan goal, plan steps, plan
outcome]
• Retrieval can be done on each dimension
– On context (plan goal)  planning
– On contents (plan steps)  plan recognition
 outcome prediction
– On outcome  root cause analysis
16
Memory Implementation - Storage
• Episodes stored unchanged (no generalization)
• Indexing
–separate on each dimension (context, contents,
outcome)
–shallow indexing (only feature types, no structure)
• Forgetting [AISB-10]
17
Memory Implementation–Retrieval
• Shallow indexing then deep semantic matching
– Shallow indexing: compute surface-level similarity
– Goal: Reduce pool of candidates
– Fast, high recall, low precision
– Deep semantic matching [Yeh-06]
– Goal: Resolve structural mismatches
– Slow, high precision
– Uses: taxonomic knowledge, transformation rules, resolves
mismatches
• Given a new stimulus and an episode computes:
– similarities and differences
– quantitative and qualitative
• store (episode)
• retrieve (stimulus, dimension)
– Returns:
–most similar prior Episodes on dimension
–match score
–how they matched stimulus
–how they differ from stimulus
– mappings from stimulus to Episode
– Has an incremental version used for recognizing of
sequences of events
Memory API
18
Goal:
–Make predictions after each observation
Applicable to:
– plan recognition, dialog understanding
Idea:
– segment episodes based on temporal links,
– recognize individual pieces
– then aggregate into episodes
– Confidence of recognized episode = a combination of:
– confidence in recognition of individual pieces
– the order in which they were observed
Incremental Recognition
19
20
Incremental Recognition Algorithm
initialize candidates
observe next action
new-candidates ← retrieve (current-action)
forall episode in new-candidates do
if episode not in candidates then
synchronize-candidate(episode, prior-actions)
forall candidate in candidates do
candidate-match ← match(curr-action, candidate)
candidate ← update-candidate(candidate-match)
candidates ← sort(candidates)
result ← sort(candidates)
make-available first-n (N, result)
EXPERIMENTAL EVALUATION
“In God we trust, all others bring data”
W Edwards Deming
22
Experimental Evaluation
 Evaluated on Three Tasks [Tecuci-Diss]
–Memory-based planning:
initial state + goal  plan
–Episodic-based goal recognition:
plan  goal schema
–Memory-based question answering:
question  answer
• Measured
–Task Performance (Precision, Recall)
–Memory performance (retrieval time, memory overhead)
• Same representation across tasks
23
Memory-Based Planning
• Problem
– Given: initial state, goal state, operators
– Find: sequence of operators that changes initial state
into goal state
• Solution:
– search (restricted: hierarchical, skeletal)
• Memory-based planning
– reuse and adapt past experience
24
Episodic-based Plan Recognition
• Plan Recognition problem:
– predict goals, intentions, future actions from observed
actions
– keyhole, intended
• Desired characteristics
– incremental, early predictions
– extensible plan library
• Approaches:
– deductive, abductive, probabilistic, case-based
25
Memory-Based Problem Solving
• Problem
– Given: KB, complex question
– Find: correct model in KB that answers question and explain
answer
• Ex: A car starts from rest and reaches 28 m/s in 2 s.
What distance does it cover?
• Questions = scenario + query
• Classical solution: search
– KB size and complexity of models makes it infeasible or
incomplete
• Memory - fast access to relevant models
26
Summary of Evaluation Results
• Accuracy – same as
– exhaustive search (planning, problem solving)
– statistical approaches (plan recognition)
• Scalability
– retrieval not proportional to memory size
• Sped-up problem solving
• Multifunctional memory structure
Watson + Memory
• Application domains: complex tasks, temporal aspect
– Dialog
– Remembering what was said
– Goal detection
– Prediction
– Robotics
– Complex behaviors
– Virtual agent
– Prediction
• Memory as a Service ?
28
Summary
• The need for memory in cognitive systems
• Separation of memory from system
– Generic, reusable memory module
– Adds episodic memory functionality to system
• Requirements
• Implementation satisfying requirements
• Evaluation
– planning, plan recognition, problem solving
• [Yeh-06] Yeh, P “Flexible semantic matching of rich knowledge structures” PhD Diss, UT Austin 2006
• [Tecuci-Flairs-09] Tecuci, D; Porter, B. “Memory-based goal schema recognition” FLAIRS 2009
• [Tecuci-AAAI-06] Using an Episodic Memory Module for Pattern Capture and Recognition.
• [Tecuci-Diss] Tecuci 2007 A Generic Memory Module for Events, PhD Diss., Univ. of Texas
• [ICBO] Palla et. al. “A Metadata approach to querying multiple biomedical ontologies” ICBO 2011
• [KCap-11] Palla et. al. “Using Answer Set Programming for Representing and Reasoning with Preferences
and Uncertainty in Dynamic Domains”
• [AI-04] Friedland et. al. 2004, Project Halo: Towards a Digital Aristotle, AI Magazine 25(4). 2004.
• [AI-10] Gunning et. al. “Project Halo update – Progress towards digital Aristotle”, AI Mag 2010
• [KR-04a] Barker et. al. 2004, A question-answering system for AP Chemistry: Assessing KR&R
Technologies. KR 2004.
• [KR-04b] Friedland et.al. 2004, Towards a Quantitative, Platform-Independent Analysis of Knowledge
Systems, KR 2004
• [AAAI-07] Barker et. al. 2007, Learning by Reading: A Prototype System, Performance Baseline and
Lessons Learned. AAAI 2007.
• [KCAP-07] Chaw et al. 2007, Capturing a Taxonomy of Failures During Automatic Interpretation of
Questions Posed in Natural Language
• [AISB-10] Nuxoll et. al Comparing Forgetting Algorithms for Artificial Episodic Memory Systems, RWWA at
AISB 2010
• [KCAP-01] P. Clark et al. Knowledge Entry as the Graphical Assembly of Components. KCAP ’01
• [HALO] Vulcan Inc. Project Halo Website http://projecthalo.com/halotempl.asp?cid=21
• [KM] The Knowledge Machine http://www.cs.utexas.edu/users/mfkb/RKF/km.html
references
29
• Thank you!

Weitere ähnliche Inhalte

Ähnlich wie "Enhancing Intelligent Agents with Episoic Memories"

1-Lec - Introduction vhvv,vbvv,v (2).ppt
1-Lec - Introduction vhvv,vbvv,v (2).ppt1-Lec - Introduction vhvv,vbvv,v (2).ppt
1-Lec - Introduction vhvv,vbvv,v (2).pptAqeelAbbas94
 
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiIvo Andreev
 
2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...
2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...
2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...Robert Richards, Ph.D.
 
Simulation and modeling introduction.pptx
Simulation and modeling introduction.pptxSimulation and modeling introduction.pptx
Simulation and modeling introduction.pptxShamasRehman4
 
COMP 775 Motion planning paper presentation
COMP 775 Motion planning paper presentation COMP 775 Motion planning paper presentation
COMP 775 Motion planning paper presentation Ravikiran J
 
InfoEducatie - Face Recognition Architecture
InfoEducatie - Face Recognition ArchitectureInfoEducatie - Face Recognition Architecture
InfoEducatie - Face Recognition ArchitectureBogdan Bocse
 
Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017
Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017
Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017VisageCloud
 
Cognitive Level of Analysis: Cognitive Processes
Cognitive Level of Analysis: Cognitive ProcessesCognitive Level of Analysis: Cognitive Processes
Cognitive Level of Analysis: Cognitive ProcessesMackenzie
 
Sdec11.agile ina day
Sdec11.agile ina daySdec11.agile ina day
Sdec11.agile ina daysdeconf
 
lecture01_Introduction.pdf
lecture01_Introduction.pdflecture01_Introduction.pdf
lecture01_Introduction.pdfMarlonMagtibay2
 
The Agile Shape-up method for collaborative developments in international con...
The Agile Shape-up method for collaborative developments in international con...The Agile Shape-up method for collaborative developments in international con...
The Agile Shape-up method for collaborative developments in international con...Daniele Bailo
 
Comparison GWAP Mechanical Turk
Comparison GWAP Mechanical TurkComparison GWAP Mechanical Turk
Comparison GWAP Mechanical TurkElena Simperl
 
4 memory management bb
4   memory management bb4   memory management bb
4 memory management bbShahid Riaz
 
Database_Design.ppt
Database_Design.pptDatabase_Design.ppt
Database_Design.pptNadiSarj2
 

Ähnlich wie "Enhancing Intelligent Agents with Episoic Memories" (20)

1-Lec - Introduction vhvv,vbvv,v (2).ppt
1-Lec - Introduction vhvv,vbvv,v (2).ppt1-Lec - Introduction vhvv,vbvv,v (2).ppt
1-Lec - Introduction vhvv,vbvv,v (2).ppt
 
Constrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project BonsaiConstrained Optimization with Genetic Algorithms and Project Bonsai
Constrained Optimization with Genetic Algorithms and Project Bonsai
 
U mpres
U mpresU mpres
U mpres
 
2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...
2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...
2010 06-07-sto-2010-intelligent-resource-scheduling-for-reduced-turnaround-du...
 
The art of project estimation
The art of project estimationThe art of project estimation
The art of project estimation
 
Simulation and modeling introduction.pptx
Simulation and modeling introduction.pptxSimulation and modeling introduction.pptx
Simulation and modeling introduction.pptx
 
Computer science Curricula 2013
Computer science Curricula 2013Computer science Curricula 2013
Computer science Curricula 2013
 
COMP 775 Motion planning paper presentation
COMP 775 Motion planning paper presentation COMP 775 Motion planning paper presentation
COMP 775 Motion planning paper presentation
 
InfoEducatie - Face Recognition Architecture
InfoEducatie - Face Recognition ArchitectureInfoEducatie - Face Recognition Architecture
InfoEducatie - Face Recognition Architecture
 
Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017
Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017
Scaling Face Recognition with Big Data - Key Notes at DevTalks Bucharest 2017
 
Cognitive Level of Analysis: Cognitive Processes
Cognitive Level of Analysis: Cognitive ProcessesCognitive Level of Analysis: Cognitive Processes
Cognitive Level of Analysis: Cognitive Processes
 
week15a.pdf
week15a.pdfweek15a.pdf
week15a.pdf
 
Sdec11.agile ina day
Sdec11.agile ina daySdec11.agile ina day
Sdec11.agile ina day
 
lecture01_Introduction.pdf
lecture01_Introduction.pdflecture01_Introduction.pdf
lecture01_Introduction.pdf
 
The Agile Shape-up method for collaborative developments in international con...
The Agile Shape-up method for collaborative developments in international con...The Agile Shape-up method for collaborative developments in international con...
The Agile Shape-up method for collaborative developments in international con...
 
Database design
Database designDatabase design
Database design
 
Comparison GWAP Mechanical Turk
Comparison GWAP Mechanical TurkComparison GWAP Mechanical Turk
Comparison GWAP Mechanical Turk
 
4 memory management bb
4   memory management bb4   memory management bb
4 memory management bb
 
Database_Design.ppt
Database_Design.pptDatabase_Design.ppt
Database_Design.ppt
 
Memory Management
Memory ManagementMemory Management
Memory Management
 

Mehr von diannepatricia

Teaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsonTeaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsondiannepatricia
 
Cognitive systems institute talk 8 june 2017 - v.1.0
Cognitive systems institute talk   8 june 2017 - v.1.0Cognitive systems institute talk   8 june 2017 - v.1.0
Cognitive systems institute talk 8 june 2017 - v.1.0diannepatricia
 
Building Compassionate Conversational Systems
Building Compassionate Conversational SystemsBuilding Compassionate Conversational Systems
Building Compassionate Conversational Systemsdiannepatricia
 
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”diannepatricia
 
Cognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving AccessibilityCognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving Accessibilitydiannepatricia
 
Artificial Intellingence in the Car
Artificial Intellingence in the CarArtificial Intellingence in the Car
Artificial Intellingence in the Cardiannepatricia
 
“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”diannepatricia
 
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...diannepatricia
 
170330 cognitive systems institute speaker series mark sherman - watson pr...
170330 cognitive systems institute speaker series    mark sherman - watson pr...170330 cognitive systems institute speaker series    mark sherman - watson pr...
170330 cognitive systems institute speaker series mark sherman - watson pr...diannepatricia
 
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”diannepatricia
 
Cognitive Assistance for the Aging
Cognitive Assistance for the AgingCognitive Assistance for the Aging
Cognitive Assistance for the Agingdiannepatricia
 
From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"diannepatricia
 
The Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented IntelligenceThe Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented Intelligencediannepatricia
 
Developing Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team CognitionDeveloping Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team Cognitiondiannepatricia
 
Cyber-Social Learning Systems
Cyber-Social Learning SystemsCyber-Social Learning Systems
Cyber-Social Learning Systemsdiannepatricia
 
“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”diannepatricia
 
"Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ..."Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ...diannepatricia
 
Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50diannepatricia
 
KATE - a Platform for Machine Learning
KATE - a Platform for Machine LearningKATE - a Platform for Machine Learning
KATE - a Platform for Machine Learningdiannepatricia
 
Cognitive Computing for Aging Society
Cognitive Computing for Aging SocietyCognitive Computing for Aging Society
Cognitive Computing for Aging Societydiannepatricia
 

Mehr von diannepatricia (20)

Teaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsonTeaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watson
 
Cognitive systems institute talk 8 june 2017 - v.1.0
Cognitive systems institute talk   8 june 2017 - v.1.0Cognitive systems institute talk   8 june 2017 - v.1.0
Cognitive systems institute talk 8 june 2017 - v.1.0
 
Building Compassionate Conversational Systems
Building Compassionate Conversational SystemsBuilding Compassionate Conversational Systems
Building Compassionate Conversational Systems
 
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
 
Cognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving AccessibilityCognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving Accessibility
 
Artificial Intellingence in the Car
Artificial Intellingence in the CarArtificial Intellingence in the Car
Artificial Intellingence in the Car
 
“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”
 
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
 
170330 cognitive systems institute speaker series mark sherman - watson pr...
170330 cognitive systems institute speaker series    mark sherman - watson pr...170330 cognitive systems institute speaker series    mark sherman - watson pr...
170330 cognitive systems institute speaker series mark sherman - watson pr...
 
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
 
Cognitive Assistance for the Aging
Cognitive Assistance for the AgingCognitive Assistance for the Aging
Cognitive Assistance for the Aging
 
From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"
 
The Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented IntelligenceThe Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented Intelligence
 
Developing Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team CognitionDeveloping Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team Cognition
 
Cyber-Social Learning Systems
Cyber-Social Learning SystemsCyber-Social Learning Systems
Cyber-Social Learning Systems
 
“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”
 
"Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ..."Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ...
 
Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50
 
KATE - a Platform for Machine Learning
KATE - a Platform for Machine LearningKATE - a Platform for Machine Learning
KATE - a Platform for Machine Learning
 
Cognitive Computing for Aging Society
Cognitive Computing for Aging SocietyCognitive Computing for Aging Society
Cognitive Computing for Aging Society
 

Kürzlich hochgeladen

Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024SynarionITSolutions
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 

Kürzlich hochgeladen (20)

Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 

"Enhancing Intelligent Agents with Episoic Memories"

  • 1. Enhancing intelligent agents with episodic memories Dan Tecuci dan.tecuci@us.ibm.com Cognitive Systems Institute Weekly Meeting Sep 8, 2016
  • 2. 2 Outline • Motivation – Human Memory – Why is episodic memory needed in a cognitive system? • Approach – Generic Episodic Memory Module – Requirements – A proposed implementation • Evaluation • Conclusions & Discussion
  • 3. WHY DO WE NEED MEMORY? “Those who cannot remember the past are condemned to repeat it.” George Santyana
  • 4. • Remembering is an essential characteristic of intelligence • Humans can – recall their past experience – Use memories to – solve similar problems – avoid unwanted behavior – recognize plans - infer other people’s goals – remember own goals and track progress • Memory and intelligence go hand in hand Why it’s important to remember the past 4
  • 5. • Experience – important knowledge source – mostly unused in current systems • Importance of experience grows with – Complexity of task – Life-expectancy of system • Eager approach (generalize & discard) – machine learning – Assumes all value can be extracted up-front • Lazy approach (store for now, use later) – Defers (part of) learning till later The Role of Memory in a Cognitive System 5
  • 6. 6 Benefits of Using Stored Memories • Memory enables a system to: –improve performance – solve problem faster by adapting previous solutions –improve competence – informed search –perform additional tasks –avoid and detect failures – monitor long-term goals – reflect on past
  • 7. 7 Human Memory - Episodic vs. Semantic • Differences – concrete vs. abstract – dated vs. timeless – personal vs. general • Similarities – knowledge is acquired through senses – automatic retention – retrieval triggered by stimuli, automatic
  • 8. 8 Episodic Memory Functions • Encoding – activation (when to store an episode) – salient feature selection (what to sore in an episode) – cue selection (what features to use as cues) • Storage – how to maintain an episode in memory (forgetting) • Retrieval – cue construction – matching – recall – recollective experience
  • 10. • Characteristics: – Generic – Same memory - different apps – Can be used for various tasks and domains – Separate from application – Interface through API – Store complex experience (e.g. temporal, graph-based) • Memory function: – Return most relevant prior episodes • Advantages: – focus on memory organization – reduce complexity of overall system PROPOSAL: Generic Memory Module 10
  • 11. • Accuracy in retrieval - retrieve memories relevant to the situation at hand • Scalability - accommodate a large number of episodes without a significant decrease in performance • Efficiency - efficient storage and retrieval (both in space and time) • Content addressability - memories should be addressable by their content • Flexible matching - recognize prior situations even if they only partially match the current one General Memory Requirements 11
  • 12. • Conceptual representation for generic events • Domain-independent storage/retrieval algorithms • Flexible interface Challenges 12
  • 13. • Episode – unit of storage – capture a complex event, with temporal extent. – represented as Conceptual graphs (sets of S-P-O triples) – Use ontology for concept representation • Divide episodes into three dimensions – context = setting of episode – contents = ordered set of events – outcome = evaluation of episode’s effects • What constitutes an episode – application Episode Representation 13
  • 14. 14 Planning Episode Example Context: “move all perl scripts to the linux folder” Contents: sh> find -name linux ./code/linux sh> find -name *.pl ./code/accessor.pl ./code/constructor.pl ./code/gang/dwarf/aml.pl sh> mv ./bin/gang/set/convert.pl ./code/accessor.pl ./code/constructor.pl ./code/gang/dwarf/aml.pl ./code/linux Outcome: “Success”
  • 15. 15 Using Stored Episodes • Episodes should be multifunctional – Same episode can be used for different purposes • E.g. Planning Episode = [plan goal, plan steps, plan outcome] • Retrieval can be done on each dimension – On context (plan goal)  planning – On contents (plan steps)  plan recognition  outcome prediction – On outcome  root cause analysis
  • 16. 16 Memory Implementation - Storage • Episodes stored unchanged (no generalization) • Indexing –separate on each dimension (context, contents, outcome) –shallow indexing (only feature types, no structure) • Forgetting [AISB-10]
  • 17. 17 Memory Implementation–Retrieval • Shallow indexing then deep semantic matching – Shallow indexing: compute surface-level similarity – Goal: Reduce pool of candidates – Fast, high recall, low precision – Deep semantic matching [Yeh-06] – Goal: Resolve structural mismatches – Slow, high precision – Uses: taxonomic knowledge, transformation rules, resolves mismatches • Given a new stimulus and an episode computes: – similarities and differences – quantitative and qualitative
  • 18. • store (episode) • retrieve (stimulus, dimension) – Returns: –most similar prior Episodes on dimension –match score –how they matched stimulus –how they differ from stimulus – mappings from stimulus to Episode – Has an incremental version used for recognizing of sequences of events Memory API 18
  • 19. Goal: –Make predictions after each observation Applicable to: – plan recognition, dialog understanding Idea: – segment episodes based on temporal links, – recognize individual pieces – then aggregate into episodes – Confidence of recognized episode = a combination of: – confidence in recognition of individual pieces – the order in which they were observed Incremental Recognition 19
  • 20. 20 Incremental Recognition Algorithm initialize candidates observe next action new-candidates ← retrieve (current-action) forall episode in new-candidates do if episode not in candidates then synchronize-candidate(episode, prior-actions) forall candidate in candidates do candidate-match ← match(curr-action, candidate) candidate ← update-candidate(candidate-match) candidates ← sort(candidates) result ← sort(candidates) make-available first-n (N, result)
  • 21. EXPERIMENTAL EVALUATION “In God we trust, all others bring data” W Edwards Deming
  • 22. 22 Experimental Evaluation  Evaluated on Three Tasks [Tecuci-Diss] –Memory-based planning: initial state + goal  plan –Episodic-based goal recognition: plan  goal schema –Memory-based question answering: question  answer • Measured –Task Performance (Precision, Recall) –Memory performance (retrieval time, memory overhead) • Same representation across tasks
  • 23. 23 Memory-Based Planning • Problem – Given: initial state, goal state, operators – Find: sequence of operators that changes initial state into goal state • Solution: – search (restricted: hierarchical, skeletal) • Memory-based planning – reuse and adapt past experience
  • 24. 24 Episodic-based Plan Recognition • Plan Recognition problem: – predict goals, intentions, future actions from observed actions – keyhole, intended • Desired characteristics – incremental, early predictions – extensible plan library • Approaches: – deductive, abductive, probabilistic, case-based
  • 25. 25 Memory-Based Problem Solving • Problem – Given: KB, complex question – Find: correct model in KB that answers question and explain answer • Ex: A car starts from rest and reaches 28 m/s in 2 s. What distance does it cover? • Questions = scenario + query • Classical solution: search – KB size and complexity of models makes it infeasible or incomplete • Memory - fast access to relevant models
  • 26. 26 Summary of Evaluation Results • Accuracy – same as – exhaustive search (planning, problem solving) – statistical approaches (plan recognition) • Scalability – retrieval not proportional to memory size • Sped-up problem solving • Multifunctional memory structure
  • 27. Watson + Memory • Application domains: complex tasks, temporal aspect – Dialog – Remembering what was said – Goal detection – Prediction – Robotics – Complex behaviors – Virtual agent – Prediction • Memory as a Service ?
  • 28. 28 Summary • The need for memory in cognitive systems • Separation of memory from system – Generic, reusable memory module – Adds episodic memory functionality to system • Requirements • Implementation satisfying requirements • Evaluation – planning, plan recognition, problem solving
  • 29. • [Yeh-06] Yeh, P “Flexible semantic matching of rich knowledge structures” PhD Diss, UT Austin 2006 • [Tecuci-Flairs-09] Tecuci, D; Porter, B. “Memory-based goal schema recognition” FLAIRS 2009 • [Tecuci-AAAI-06] Using an Episodic Memory Module for Pattern Capture and Recognition. • [Tecuci-Diss] Tecuci 2007 A Generic Memory Module for Events, PhD Diss., Univ. of Texas • [ICBO] Palla et. al. “A Metadata approach to querying multiple biomedical ontologies” ICBO 2011 • [KCap-11] Palla et. al. “Using Answer Set Programming for Representing and Reasoning with Preferences and Uncertainty in Dynamic Domains” • [AI-04] Friedland et. al. 2004, Project Halo: Towards a Digital Aristotle, AI Magazine 25(4). 2004. • [AI-10] Gunning et. al. “Project Halo update – Progress towards digital Aristotle”, AI Mag 2010 • [KR-04a] Barker et. al. 2004, A question-answering system for AP Chemistry: Assessing KR&R Technologies. KR 2004. • [KR-04b] Friedland et.al. 2004, Towards a Quantitative, Platform-Independent Analysis of Knowledge Systems, KR 2004 • [AAAI-07] Barker et. al. 2007, Learning by Reading: A Prototype System, Performance Baseline and Lessons Learned. AAAI 2007. • [KCAP-07] Chaw et al. 2007, Capturing a Taxonomy of Failures During Automatic Interpretation of Questions Posed in Natural Language • [AISB-10] Nuxoll et. al Comparing Forgetting Algorithms for Artificial Episodic Memory Systems, RWWA at AISB 2010 • [KCAP-01] P. Clark et al. Knowledge Entry as the Graphical Assembly of Components. KCAP ’01 • [HALO] Vulcan Inc. Project Halo Website http://projecthalo.com/halotempl.asp?cid=21 • [KM] The Knowledge Machine http://www.cs.utexas.edu/users/mfkb/RKF/km.html references 29