Deep learning - a primer

Uwe Friedrichsen
Uwe Friedrichsencodecentric AG
Deep learning
A primer for the curious developer

Uwe Friedrichsen & Dr. Shirin Glander –codecentric AG – 2018
@ufried

Uwe Friedrichsen

uwe.friedrichsen@codecentric.de
@ShirinGlander

Dr. Shirin Glander

shirin.glander@codecentric.de
Why should I care about Deep Learning?
Deep learning has the potential to affect white collar workers (including IT)
in a similar way as robots affected blue collar workers.
What is Deep Learning?

Some success stories
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
What is Deep Learning?

A rough classification
AI

Artificial
Intelligence
ML

Machine
Learning
RL

Representational
Learning
DL

Deep
Learning
Traditional AI




Focus on problems that are ...
•  ... hard for humans
•  ... straightforward for computers
•  ... can be formally described
Deep Learning




Focus on problems that are ...
•  ... intuitive for humans
•  ... difficult for computers
(hard to be described formally)
•  ... best learnt from experience
Where does Deep Learning come from?
General evolution


•  Two opposed forces
•  Recreation of biological neural processing
•  Abstract mathematical models (mostly linear algebra)
•  Results in different models and algorithms
•  No clear winner yet
Cybernetics (ca. 1940 - 1960)

•  ADALINE, Perceptron
•  Linear models, typically no hidden layers
•  Stochastic Gradient Descent (SGD)
•  Limited applicability
•  E.g., ADALINE could not learn XOR
•  Resulted in “First winter of ANN” (Artificial Neural Networks)
Connectionism (ca. 1980 - 1990)

•  Neocognitron
•  Non-linear models, distributed feature representation
•  Backpropagation
•  Typically 1, rarely more hidden layers
•  First approaches of sequence modeling
•  LSTM (Long short-term memory) in 1997
•  Unrealistic expectations nurtured by ventures
•  Resulted in “Second winter of ANN”
Deep Learning (ca. 2006 -)


•  Improved algorithms, advanced computing power
•  Enabled training much larger and deeper networks
•  Enabled training much larger data sets
•  Typically several to many hidden layers
•  Overcame the “feature extraction dilemma”
What is Deep Learning used for?
Deep Learning application areas




•  Classification (incl. missing inputs)
•  Regression (value prediction)
•  Function prediction
•  Density estimation
•  Structured output (e.g., translation)





•  Anomaly detection
•  Synthesis and sampling
•  Denoising
•  Compression (dimension reduction)
•  ...
How does Deep Learning work?

A first (scientifically inspired) approach
„A computer program is said to learn
•  from experience E
•  with respect to some class of tasks T
•  and performance measure P
if its performance at tasks in T,
as measured by P,
improves with experience E.”

-- T. Mitchell, Machine Learning, p. 2, McGraw Hill (1997)
Supervised learning,
unsupervised learning,
reinforcement learning, ...
Too difficult to solve
with fixed programs
designed by humans
Accuracy vs. error rate,
training vs. test set, ...
Err ...
Hmm ...
Well ...
I don’t get it!
How does Deep Learning work?

A second (more down-to-earth) approach
Operating
principle
Training
Network
types
Deep
Learning
Deep
Learning
Operating
principle
Training
Network
types
Structure
Behavior
Weight
Operation
Neuron
Data
CNN
Types
Challenges
Quality
measure
RNN
 LSTM
Auto-
encoder
GAN
MLP
Training
set
Cost
function
Transfer
learning
Regulari-
zation
Layer
Connection
Hyper-
parameter
Activation
function
Reinforce-
ment
Unsuper-
vised
Supervised
Stochastic
gradient
descent
Back-
propagation
Under-/
Overfitting
Validation/
Test set
Optimization
procedure
Deep
Learning
Operating
principle
Training
Network
types
Structure
Behavior
Operating
principle
Structure
Behavior
Operating
principle
Operating
principle
Structure
Behavior
Neuron
Neuron

•  Design inspired by biological neurons
•  One or more inputs
•  Processing (and state storage) unit
•  One or more outputs
•  In practice often implemented as tensor transformations
•  Relevance of internal state depends on network type
•  Usually negligible for feed-forward networks
•  Usually relevant for recurrent networks
Neuron

Processing

(+ State)
Output(s)
Input(s)
...
...
Layer
Operating
principle
Structure
Behavior
Neuron
Layer

•  Neurons typically organized in layers
•  Input and output layer as default
•  Optionally one or more hidden layer
•  Layer layout can have 1-n dimensions
•  Neurons in different layers can have different properties
•  Different layers responsible for different (sub-)tasks
Output layer
Input layer
...
N
1
2
Hidden layer(s)
...
Connection
Operating
principle
Structure
Behavior
Neuron
Layer
Connection

•  Usually connect input and output tensor in a 1:1 manner
•  Connect between layers (output layer N-1 à input layer N)
•  Layers can be fully or partially (sparsely) connected
•  RNNs also have backward and/or self connections
•  Some networks have connections between neurons
of the same layer (e.g., Hopfield nets, Boltzmann machines)
Input tensor(s)
Output tensor(s)
Weight
Operating
principle
Structure
Behavior
Neuron
Layer
Connection
Weight

•  (Logically) augments a connection
•  Used to amplify or dampen a signal sent over a connection
•  The actual “memory” of the network
•  The “right” values of the weights are learned during training
•  Can also be used to introduce a bias for a neuron
•  By connecting it to an extra neuron that constantly emits 1
W
 Weight
Operation
Operating
principle
Structure
Behavior
Neuron
Layer
Weight
Connection
Input tensor(s)
Output tensor(s)
Step 1

•  For each neuron of input layer
•  Copy resp. input tensor’s value to neuron’s input
•  Calculate state/output using activation function
(typically linear function, passing value through)
Step 2-N

•  For each hidden layer and output layer in their order
•  For each neuron of the layer
•  Calculate weighted sum on inputs
•  Calculate state/output using activation function
(see examples later)
Final step

•  For each neuron of output layer
•  Copy neuron’s output to resp. output tensor’s value
Input tensor(s)
Output tensor(s)
Step 1
Final step
Step 2-N
•  Default update procedure (most widespread)
•  All neuron per layer in parallel
•  Different update procedures exist
•  E.g., some Hopfield net implementations
randomly pick neurons for update
Activation
function
Operating
principle
Structure
Behavior
Neuron
Layer
Weight
Connection
Operation
Linear function

•  Easy to handle
•  Cannot handle
non-linear problems
Logistic sigmoid function

•  Very widespread
•  Delimits output to [0, 1]
•  Vanishing gradient
problem
Hyperbolic tangent

•  Very widespread
•  Delimits output to [-1, 1]
•  Vanishing gradient
problem
Rectified linear unit (ReLU)

•  Easy to handle
•  No derivative in 0
•  Dying ReLU problem
•  Can be mitigated, e.g.,
by using leaky ReLU
Softplus

•  Smooth approximation
of ReLU
•  ReLU usually performs
better
•  Thus, use of softplus
usually discouraged
Hyper-
parameter
Operating
principle
Structure
Behavior
Neuron
Layer
Weight
Connection
Operation
Activation
function
Hyperparameter


•  Influence network and algorithm behavior
•  Often influence model capacity
•  Not learned, but usually manually optimized
•  Currently quite some research interest in
automatic hyperparameter optimization
Examples

•  Number of hidden layers
•  Number of hidden units
•  Learning rate
•  Number of clusters
•  Weight decay coefficient
•  Convolution kernel width
•  ...
Training
Deep
Learning
Operating
principle
Network
types
Structure
Behavior
Weight
Operation
Neuron
Layer
Connection
Hyper-
parameter
Activation
function
Quality
measure
Training
Cost function
Training
Quality
measure
Cost function (a.k.a. loss function)

•  Determines distance from optimal performance
•  Mean squared error as simple (and widespread) example
Cost function (a.k.a. loss function)

•  Determines distance from optimal performance
•  Mean squared error as simple (and widespread) example
•  Often augmented with regularization term
for better generalization (see challenges)
Optimization
procedure
Training
Quality
measure
Cost function
Training
Quality
measure
Stochastic
gradient
descent
Cost function
Optimization
procedure
Stochastic gradient descent

•  Direct calculation of minimum often not feasible
•  Instead stepwise “descent” using the gradient
à Gradient descent
Stochastic gradient descent

•  Direct calculation of minimum often not feasible
•  Instead stepwise “descent” using the gradient
à Gradient descent
•  Not feasible for large training sets
•  Use (small) random sample of training set per iteration
à Stochastic gradient descent (SGD)
Stochastic gradient descent
Gradient
Direction
Steepness
x
Stochastic gradient descent
x
ε * gradient
x’
Learning
rate ε
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Cost function
Optimization
procedure
Backpropagation

•  Procedure to calculate new weights based on loss function
Depends on
cost function
Depends on
activation function
Depends on
input calculation
Backpropagation

•  Procedure to calculate new weights based on loss function
•  Usually “back-propagated” layer-wise
•  Most widespread optimization procedure
Depends on
cost function
Depends on
activation function
Depends on
input calculation
Data
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Cost function
Optimization
procedure
Training set
Validation/
Test set
Data
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Cost function
Optimization
procedure
Data set

•  Consists of examples (a.k.a. data points)
•  Example always contains input tensor
•  Sometimes also contains expected output tensor
(depending on training type)
•  Data set usually split up in several parts
•  Training set – optimize accuracy (always used)
•  Test set – test generalization (often used)
•  Validation set – tune hyperparameters (sometimes used)
Data
Types
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Supervised
Data
Types
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Supervised learning

•  Typically learns from a large, yet finite set of examples
•  Examples consist of input and output tensor
•  Output tensor describes desired output
•  Output tensor also called label or target
•  Typical application areas
•  Classification
•  Regression and function prediction
•  Structured output problems
Unsupervised
Data
Types
Supervised
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Unsupervised learning

•  Typically learns from a large, yet finite set of examples
•  Examples consist of input tensor only
•  Learning algorithm tries to learn useful properties of the data
•  Requires different type of cost functions
•  Typical application areas
•  Clustering, density estimations
•  Denoising, compression (dimension reduction)
•  Synthesis and sampling
Reinforcement
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Reinforcement learning

•  Continuously optimizes interaction with an environment
based on reward-based learning
Agent
Environment
State t
 Reward t
State t+1
 Reward t+1
Action t
Reinforcement learning

•  Continuously optimizes interaction with an environment
based on reward-based learning
•  Goal is selection of action with highest expected reward
•  Takes (discounted) expected future rewards into account
•  Labeling of examples replaced by reward function
•  Can continuously learn à data set can be infinite
•  Typically used to solve complex tasks in (increasingly)
complex environments with (very) limited feedback
Challenges
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Under-/
Overfitting
Training set
Validation/
Test set
Cost function
Challenges
Optimization
procedure
Underfitting and Overfitting

•  Training error describes how good training data is learnt
•  Test error is an indicator for generalization capability
•  Core challenge for all machine learning type algorithms
1.  Make training error small
2.  Make gap between training and test error small
•  Underfitting is the violation of #1
•  Overfitting is the violation of #2
Good fit
Underfitting
 Overfitting
Training data
 Test data
Underfitting and Overfitting



•  Under- and overfitting influenced by model capacity
•  Too low capacity usually leads to underfitting
•  Too high capacity usually leads to overfitting
•  Finding the right capacity is a challenge
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Under-/
Overfitting
Training set
Validation/
Test set
Cost function
Regularization
Challenges
Optimization
procedure
Regularization

•  Regularization is a modification applied to learning algorithm
•  to reduce the generalization error
•  but not the training error
•  Weight decay is a typical regularization measure
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Under-/
Overfitting
Transfer
learning
Training set
Validation/
Test set
Cost function
Regularization
Challenges
Optimization
procedure
Transfer learning


•  How to transfer insights between related tasks
•  E.g., is it possible to transfer knowledge gained while training
to recognize cars on the problem of recognizing trucks?
•  General machine learning problem
•  Subject of many research activities
Network
types
Deep
Learning
Operating
principle
Training
Structure
Behavior
Weight
Operation
Neuron
Data
Types
Challenges
Quality
measure
Training
set
Cost
function
Transfer
learning
Regulari-
zation
Layer
Connection
Hyper-
parameter
Activation
function
Reinforce-
ment
Unsuper-
vised
Supervised
Stochastic
gradient
descent
Back-
propagation
Under-/
Overfitting
Validation/
Test set
Optimization
procedure
MLP

Multilayer
Perceptron
Network
types
Multilayer perceptron (MLP)

•  Multilayer feed-forward networks
•  “Vanilla” neural networks
•  Typically used for
•  Function approximation
•  Regression
•  Classification
Image source: https://deeplearning4j.org
CNN

Convolutional
Neural Network
Network
types
MLP

Multilayer
Perceptron
Convolutional neural network (CNN)

•  Special type of MLP for image processing
•  Connects convolutional neuron only with receptive field
•  Advantages
•  Less computing
power required
•  Often even better
recognition rates
•  Inspired by organization of visual cortex
Image source: https://deeplearning4j.org
RNN

Recurrent
Neural Network
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
Recurrent neural network (RNN)

•  Implements internal feedback loops
•  Provides a temporal memory
•  Typically used for
•  Speech recognition
•  Text recognition
•  Time series processing
Image source: https://deeplearning4j.org
LSTM

Long
Short-Term
Memory
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
RNN

Recurrent
Neural Network
Long short-term memory (LSTM)

•  Special type of RNN
•  Uses special LSTM units
•  Can implement very long-term memory
while avoiding the vanishing/exploding
gradient problem
•  Same application areas as RNN
Image source: https://deeplearning4j.org
Auto-
encoder
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
RNN

Recurrent
Neural Network
LSTM

Long
Short-Term
Memory
Autoencoder
•  Special type of MLP
•  Reproduces input at output layer
•  Consists of encoder and decoder
•  Usually configured undercomplete
•  Learns efficient feature codings
•  Dimension reduction (incl. compression)
•  Denoising
•  Usually needs pre-training for not only
reconstructing average of training set
Image source: https://deeplearning4j.org
GAN

Generative
Adversarial
Networks
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
RNN

Recurrent
Neural Network
Auto-
encoder
LSTM

Long
Short-Term
Memory
Generative adversarial networks (GAN)
•  Consists of two (adversarial) networks
•  Generator creating fake images
•  Discriminator trying to identify
fake images
•  Typically used for
•  Synthesis and sampling
(e.g., textures in games)
•  Structured output with variance (e.g., variations of a design or voice generation)
•  Probably best known for creating fake celebrity images
Image source: https://deeplearning4j.org
Deep
Learning
Operating
principle
Training
Network
types
Structure
Behavior
Weight
Operation
Neuron
Data
CNN
Types
Challenges
Quality
measure
RNN
 LSTM
Auto-
encoder
GAN
MLP
Training
set
Cost
function
Transfer
learning
Regulari-
zation
Layer
Connection
Hyper-
parameter
Activation
function
Reinforce-
ment
Unsuper-
vised
Supervised
Stochastic
gradient
descent
Back-
propagation
Under-/
Overfitting
Validation/
Test set
Optimization
procedure
How does Deep Learning feel in practice?
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
Deep learning - a primer
What issues might I face if diving deeper?
Issues you might face

•  Very fast moving research domain
•  You need the math. Really!
•  How much data do you have?
•  GDPR: Can you explain the decision of your network?
•  Meta-Learning as the next step
•  Monopolization of research and knowledge
Wrap-up
Wrap-up

•  Broad, diverse topic
•  Very good library support and more
•  Very active research topic
•  No free lunch
•  You need the math!

à Exciting and important topic – become a part of it!
References

•  I. Goodfellow, Y. Bengio, A. Courville, ”Deep learning",
MIT press, 2016, also available via https://www.deeplearningbook.org
•  C. Perez, “The Deep Learning AI Playbook”,
Intuition Machine Inc., 2017
•  F. Chollet, "Deep Learning with Python",
Manning Publications, 2017
•  OpenAI, https://openai.com
•  Keras, https://keras.io
•  Deep Learning for Java, https://deeplearning4j.org/index.html
•  Deep Learning (Resource site), http://deeplearning.net
@ShirinGlander

Dr. Shirin Glander

shirin.glander@codecentric.de
@ufried

Uwe Friedrichsen

uwe.friedrichsen@codecentric.de
1 von 137

Recomendados

Real-world consistency explained von
Real-world consistency explainedReal-world consistency explained
Real-world consistency explainedUwe Friedrichsen
2.9K views60 Folien
Digitization solutions - A new breed of software von
Digitization solutions - A new breed of softwareDigitization solutions - A new breed of software
Digitization solutions - A new breed of softwareUwe Friedrichsen
1.8K views54 Folien
Excavating the knowledge of our ancestors von
Excavating the knowledge of our ancestorsExcavating the knowledge of our ancestors
Excavating the knowledge of our ancestorsUwe Friedrichsen
2.7K views95 Folien
The Hurricane's Butterfly: Debugging pathologically performing systems von
The Hurricane's Butterfly: Debugging pathologically performing systemsThe Hurricane's Butterfly: Debugging pathologically performing systems
The Hurricane's Butterfly: Debugging pathologically performing systemsbcantrill
5.7K views27 Folien
SRVision 2019, Utrecht: Swarming and Cynefin von
SRVision 2019, Utrecht: Swarming and CynefinSRVision 2019, Utrecht: Swarming and Cynefin
SRVision 2019, Utrecht: Swarming and CynefinJon Stevens-Hall
979 views37 Folien
Debugging (Docker) containers in production von
Debugging (Docker) containers in productionDebugging (Docker) containers in production
Debugging (Docker) containers in productionbcantrill
5.1K views42 Folien

Más contenido relacionado

Was ist angesagt?

SDI19: Swarming and Devops for ITSM von
SDI19: Swarming and Devops for ITSMSDI19: Swarming and Devops for ITSM
SDI19: Swarming and Devops for ITSMJon Stevens-Hall
232 views48 Folien
CS101- Introduction to Computing- Lecture 45 von
CS101- Introduction to Computing- Lecture 45CS101- Introduction to Computing- Lecture 45
CS101- Introduction to Computing- Lecture 45Bilal Ahmed
790 views61 Folien
Zebras all the way down: The engineering challenges of the data path von
Zebras all the way down: The engineering challenges of the data pathZebras all the way down: The engineering challenges of the data path
Zebras all the way down: The engineering challenges of the data pathbcantrill
17.1K views22 Folien
DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S... von
DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S...DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S...
DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S...Jon Stevens-Hall
438 views40 Folien
DevOps Enterprise Summit 2019 - How Swarming Enables Enterprise Support to wo... von
DevOps Enterprise Summit 2019 - How Swarming Enables EnterpriseSupport to wo...DevOps Enterprise Summit 2019 - How Swarming Enables EnterpriseSupport to wo...
DevOps Enterprise Summit 2019 - How Swarming Enables Enterprise Support to wo...Jon Stevens-Hall
966 views41 Folien
Graphel: A Purely Functional Approach to Digital Interaction von
Graphel: A Purely Functional Approach to Digital InteractionGraphel: A Purely Functional Approach to Digital Interaction
Graphel: A Purely Functional Approach to Digital Interactionmtrimpe
714 views53 Folien

Was ist angesagt?(20)

CS101- Introduction to Computing- Lecture 45 von Bilal Ahmed
CS101- Introduction to Computing- Lecture 45CS101- Introduction to Computing- Lecture 45
CS101- Introduction to Computing- Lecture 45
Bilal Ahmed790 views
Zebras all the way down: The engineering challenges of the data path von bcantrill
Zebras all the way down: The engineering challenges of the data pathZebras all the way down: The engineering challenges of the data path
Zebras all the way down: The engineering challenges of the data path
bcantrill17.1K views
DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S... von Jon Stevens-Hall
DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S...DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S...
DevOps Enterprise Summit Las Vegas 2018: The Problem of Becoming a 3rd-Line S...
Jon Stevens-Hall438 views
DevOps Enterprise Summit 2019 - How Swarming Enables Enterprise Support to wo... von Jon Stevens-Hall
DevOps Enterprise Summit 2019 - How Swarming Enables EnterpriseSupport to wo...DevOps Enterprise Summit 2019 - How Swarming Enables EnterpriseSupport to wo...
DevOps Enterprise Summit 2019 - How Swarming Enables Enterprise Support to wo...
Jon Stevens-Hall966 views
Graphel: A Purely Functional Approach to Digital Interaction von mtrimpe
Graphel: A Purely Functional Approach to Digital InteractionGraphel: A Purely Functional Approach to Digital Interaction
Graphel: A Purely Functional Approach to Digital Interaction
mtrimpe714 views
Support at scale in a DevOps world How Swarming and Cynefin can save you from... von Jon Stevens-Hall
Support at scale in a DevOps world How Swarming and Cynefin can save you from...Support at scale in a DevOps world How Swarming and Cynefin can save you from...
Support at scale in a DevOps world How Swarming and Cynefin can save you from...
Jon Stevens-Hall493 views
CAP Theorem and Split Brain Syndrome von Dilum Bandara
CAP Theorem and Split Brain SyndromeCAP Theorem and Split Brain Syndrome
CAP Theorem and Split Brain Syndrome
Dilum Bandara1.1K views
Service Manager Dag, Netherlands 2018: Why we should ditch the 3-tier support... von Jon Stevens-Hall
Service Manager Dag, Netherlands 2018: Why we should ditch the 3-tier support...Service Manager Dag, Netherlands 2018: Why we should ditch the 3-tier support...
Service Manager Dag, Netherlands 2018: Why we should ditch the 3-tier support...
Jon Stevens-Hall577 views
Mock Objects, Design and Dependency Inversion Principle von P Heinonen
Mock Objects, Design and Dependency Inversion PrincipleMock Objects, Design and Dependency Inversion Principle
Mock Objects, Design and Dependency Inversion Principle
P Heinonen2.8K views
Devops In The Enterprise: How Swarming Can Fix The Problem Of Becoming A 3rd-... von Jon Stevens-Hall
Devops In The Enterprise:How Swarming Can Fix The Problem Of Becoming A 3rd-...Devops In The Enterprise:How Swarming Can Fix The Problem Of Becoming A 3rd-...
Devops In The Enterprise: How Swarming Can Fix The Problem Of Becoming A 3rd-...
Jon Stevens-Hall467 views
Swarming: How a new approach to support can save DevOps teams from 3rd-line t... von Jon Stevens-Hall
Swarming: How a new approach to support can save DevOps teams from 3rd-line t...Swarming: How a new approach to support can save DevOps teams from 3rd-line t...
Swarming: How a new approach to support can save DevOps teams from 3rd-line t...
Jon Stevens-Hall651K views
Designing for the Cloud Tutorial - QCon SF 2009 von Stuart Charlton
Designing for the Cloud Tutorial - QCon SF 2009Designing for the Cloud Tutorial - QCon SF 2009
Designing for the Cloud Tutorial - QCon SF 2009
Stuart Charlton945 views
8 Things That Make Continuous Delivery Go Nuts von Eduards Sizovs
8 Things That Make Continuous Delivery Go Nuts8 Things That Make Continuous Delivery Go Nuts
8 Things That Make Continuous Delivery Go Nuts
Eduards Sizovs2.7K views
The Diabolical Developers Guide to Performance Tuning von jClarity
The Diabolical Developers Guide to Performance TuningThe Diabolical Developers Guide to Performance Tuning
The Diabolical Developers Guide to Performance Tuning
jClarity359 views
Xen Project Contributor Training Part2 : Processes and Conventions v1.1 von The Linux Foundation
Xen Project Contributor Training Part2 : Processes and Conventions v1.1Xen Project Contributor Training Part2 : Processes and Conventions v1.1
Xen Project Contributor Training Part2 : Processes and Conventions v1.1
The Linux Foundation75.5K views
Game Development Challenges von Nick Pruehs
Game Development ChallengesGame Development Challenges
Game Development Challenges
Nick Pruehs1.1K views

Similar a Deep learning - a primer

Deep Learning Sample Class (Jon Lederman) von
Deep Learning Sample Class (Jon Lederman)Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)Jon Lederman
214 views57 Folien
Visualization of Deep Learning von
Visualization of Deep LearningVisualization of Deep Learning
Visualization of Deep LearningYaminiAlapati1
158 views44 Folien
EssentialsOfMachineLearning.pdf von
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfAnkita Tiwari
15 views65 Folien
Deep learning von
Deep learningDeep learning
Deep learningRatnakar Pandey
11.4K views21 Folien
Introduction to Deep learning and H2O for beginner's von
Introduction to Deep learning and H2O for beginner'sIntroduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sVidyasagar Bhargava
351 views30 Folien
DEF CON 24 - Clarence Chio - machine duping 101 von
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101Felipe Prado
70 views55 Folien

Similar a Deep learning - a primer(20)

Deep Learning Sample Class (Jon Lederman) von Jon Lederman
Deep Learning Sample Class (Jon Lederman)Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)
Jon Lederman214 views
Visualization of Deep Learning von YaminiAlapati1
Visualization of Deep LearningVisualization of Deep Learning
Visualization of Deep Learning
YaminiAlapati1158 views
EssentialsOfMachineLearning.pdf von Ankita Tiwari
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdf
Ankita Tiwari15 views
Introduction to Deep learning and H2O for beginner's von Vidyasagar Bhargava
Introduction to Deep learning and H2O for beginner'sIntroduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner's
DEF CON 24 - Clarence Chio - machine duping 101 von Felipe Prado
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
Felipe Prado70 views
Machine Duping 101: Pwning Deep Learning Systems von Clarence Chio
Machine Duping 101: Pwning Deep Learning SystemsMachine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning Systems
Clarence Chio1.9K views
Deep learning from a novice perspective von Anirban Santara
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
Anirban Santara1.2K views
Separating Hype from Reality in Deep Learning with Sameer Farooqui von Databricks
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
Databricks970 views
V2.0 open power ai virtual university deep learning and ai introduction von Ganesan Narayanasamy
V2.0 open power ai virtual university   deep learning and ai introductionV2.0 open power ai virtual university   deep learning and ai introduction
V2.0 open power ai virtual university deep learning and ai introduction
Deep learning: the future of recommendations von Balázs Hidasi
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendations
Balázs Hidasi15.1K views
Machine learning for IoT - unpacking the blackbox von Ivo Andreev
Machine learning for IoT - unpacking the blackboxMachine learning for IoT - unpacking the blackbox
Machine learning for IoT - unpacking the blackbox
Ivo Andreev21.6K views
Introduction to deep learning von Vishwas Lele
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Vishwas Lele261 views
Hyperparameter Tuning von Jon Lederman
Hyperparameter TuningHyperparameter Tuning
Hyperparameter Tuning
Jon Lederman2.9K views
Deep learning Introduction and Basics von Nitin Mishra
Deep learning  Introduction and BasicsDeep learning  Introduction and Basics
Deep learning Introduction and Basics
Nitin Mishra95 views

Más de Uwe Friedrichsen

Timeless design in a cloud-native world von
Timeless design in a cloud-native worldTimeless design in a cloud-native world
Timeless design in a cloud-native worldUwe Friedrichsen
8.7K views108 Folien
Life after microservices von
Life after microservicesLife after microservices
Life after microservicesUwe Friedrichsen
20.9K views97 Folien
The hitchhiker's guide for the confused developer von
The hitchhiker's guide for the confused developerThe hitchhiker's guide for the confused developer
The hitchhiker's guide for the confused developerUwe Friedrichsen
2.8K views114 Folien
The 7 quests of resilient software design von
The 7 quests of resilient software designThe 7 quests of resilient software design
The 7 quests of resilient software designUwe Friedrichsen
8.2K views87 Folien
The truth about "You build it, you run it!" von
The truth about "You build it, you run it!"The truth about "You build it, you run it!"
The truth about "You build it, you run it!"Uwe Friedrichsen
14.1K views84 Folien
The promises and perils of microservices von
The promises and perils of microservicesThe promises and perils of microservices
The promises and perils of microservicesUwe Friedrichsen
4.5K views94 Folien

Más de Uwe Friedrichsen(20)

Timeless design in a cloud-native world von Uwe Friedrichsen
Timeless design in a cloud-native worldTimeless design in a cloud-native world
Timeless design in a cloud-native world
Uwe Friedrichsen8.7K views
The hitchhiker's guide for the confused developer von Uwe Friedrichsen
The hitchhiker's guide for the confused developerThe hitchhiker's guide for the confused developer
The hitchhiker's guide for the confused developer
Uwe Friedrichsen2.8K views
The 7 quests of resilient software design von Uwe Friedrichsen
The 7 quests of resilient software designThe 7 quests of resilient software design
The 7 quests of resilient software design
Uwe Friedrichsen8.2K views
The truth about "You build it, you run it!" von Uwe Friedrichsen
The truth about "You build it, you run it!"The truth about "You build it, you run it!"
The truth about "You build it, you run it!"
Uwe Friedrichsen14.1K views
The promises and perils of microservices von Uwe Friedrichsen
The promises and perils of microservicesThe promises and perils of microservices
The promises and perils of microservices
Uwe Friedrichsen4.5K views
Resilient Functional Service Design von Uwe Friedrichsen
Resilient Functional Service DesignResilient Functional Service Design
Resilient Functional Service Design
Uwe Friedrichsen6.7K views
Resilience reloaded - more resilience patterns von Uwe Friedrichsen
Resilience reloaded - more resilience patternsResilience reloaded - more resilience patterns
Resilience reloaded - more resilience patterns
Uwe Friedrichsen7K views
DevOps is not enough - Embedding DevOps in a broader context von Uwe Friedrichsen
DevOps is not enough - Embedding DevOps in a broader contextDevOps is not enough - Embedding DevOps in a broader context
DevOps is not enough - Embedding DevOps in a broader context
Uwe Friedrichsen35.6K views
Towards complex adaptive architectures von Uwe Friedrichsen
Towards complex adaptive architecturesTowards complex adaptive architectures
Towards complex adaptive architectures
Uwe Friedrichsen2.9K views
Conway's law revisited - Architectures for an effective IT von Uwe Friedrichsen
Conway's law revisited - Architectures for an effective ITConway's law revisited - Architectures for an effective IT
Conway's law revisited - Architectures for an effective IT
Uwe Friedrichsen5.7K views
Microservices - stress-free and without increased heart attack risk von Uwe Friedrichsen
Microservices - stress-free and without increased heart attack riskMicroservices - stress-free and without increased heart attack risk
Microservices - stress-free and without increased heart attack risk
Uwe Friedrichsen4.9K views
Modern times - architectures for a Next Generation of IT von Uwe Friedrichsen
Modern times - architectures for a Next Generation of ITModern times - architectures for a Next Generation of IT
Modern times - architectures for a Next Generation of IT
Uwe Friedrichsen3.5K views
Why resilience - A primer at varying flight altitudes von Uwe Friedrichsen
Why resilience - A primer at varying flight altitudesWhy resilience - A primer at varying flight altitudes
Why resilience - A primer at varying flight altitudes
Uwe Friedrichsen3.4K views

Último

Top 10 Strategic Technologies in 2024: AI and Automation von
Top 10 Strategic Technologies in 2024: AI and AutomationTop 10 Strategic Technologies in 2024: AI and Automation
Top 10 Strategic Technologies in 2024: AI and AutomationAutomationEdge Technologies
14 views14 Folien
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze von
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng TszeDigital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng TszeNUS-ISS
19 views47 Folien
Attacking IoT Devices from a Web Perspective - Linux Day von
Attacking IoT Devices from a Web Perspective - Linux Day Attacking IoT Devices from a Web Perspective - Linux Day
Attacking IoT Devices from a Web Perspective - Linux Day Simone Onofri
15 views68 Folien
PharoJS - Zürich Smalltalk Group Meetup November 2023 von
PharoJS - Zürich Smalltalk Group Meetup November 2023PharoJS - Zürich Smalltalk Group Meetup November 2023
PharoJS - Zürich Smalltalk Group Meetup November 2023Noury Bouraqadi
120 views17 Folien
How to reduce cold starts for Java Serverless applications in AWS at JCON Wor... von
How to reduce cold starts for Java Serverless applications in AWS at JCON Wor...How to reduce cold starts for Java Serverless applications in AWS at JCON Wor...
How to reduce cold starts for Java Serverless applications in AWS at JCON Wor...Vadym Kazulkin
75 views64 Folien
DALI Basics Course 2023 von
DALI Basics Course  2023DALI Basics Course  2023
DALI Basics Course 2023Ivory Egg
14 views12 Folien

Último(20)

Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze von NUS-ISS
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng TszeDigital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze
NUS-ISS19 views
Attacking IoT Devices from a Web Perspective - Linux Day von Simone Onofri
Attacking IoT Devices from a Web Perspective - Linux Day Attacking IoT Devices from a Web Perspective - Linux Day
Attacking IoT Devices from a Web Perspective - Linux Day
Simone Onofri15 views
PharoJS - Zürich Smalltalk Group Meetup November 2023 von Noury Bouraqadi
PharoJS - Zürich Smalltalk Group Meetup November 2023PharoJS - Zürich Smalltalk Group Meetup November 2023
PharoJS - Zürich Smalltalk Group Meetup November 2023
Noury Bouraqadi120 views
How to reduce cold starts for Java Serverless applications in AWS at JCON Wor... von Vadym Kazulkin
How to reduce cold starts for Java Serverless applications in AWS at JCON Wor...How to reduce cold starts for Java Serverless applications in AWS at JCON Wor...
How to reduce cold starts for Java Serverless applications in AWS at JCON Wor...
Vadym Kazulkin75 views
DALI Basics Course 2023 von Ivory Egg
DALI Basics Course  2023DALI Basics Course  2023
DALI Basics Course 2023
Ivory Egg14 views
Emerging & Future Technology - How to Prepare for the Next 10 Years of Radica... von NUS-ISS
Emerging & Future Technology - How to Prepare for the Next 10 Years of Radica...Emerging & Future Technology - How to Prepare for the Next 10 Years of Radica...
Emerging & Future Technology - How to Prepare for the Next 10 Years of Radica...
NUS-ISS16 views
Understanding GenAI/LLM and What is Google Offering - Felix Goh von NUS-ISS
Understanding GenAI/LLM and What is Google Offering - Felix GohUnderstanding GenAI/LLM and What is Google Offering - Felix Goh
Understanding GenAI/LLM and What is Google Offering - Felix Goh
NUS-ISS41 views
The Importance of Cybersecurity for Digital Transformation von NUS-ISS
The Importance of Cybersecurity for Digital TransformationThe Importance of Cybersecurity for Digital Transformation
The Importance of Cybersecurity for Digital Transformation
NUS-ISS27 views
Beyond the Hype: What Generative AI Means for the Future of Work - Damien Cum... von NUS-ISS
Beyond the Hype: What Generative AI Means for the Future of Work - Damien Cum...Beyond the Hype: What Generative AI Means for the Future of Work - Damien Cum...
Beyond the Hype: What Generative AI Means for the Future of Work - Damien Cum...
NUS-ISS34 views
Empathic Computing: Delivering the Potential of the Metaverse von Mark Billinghurst
Empathic Computing: Delivering  the Potential of the MetaverseEmpathic Computing: Delivering  the Potential of the Metaverse
Empathic Computing: Delivering the Potential of the Metaverse
Mark Billinghurst470 views
Data-centric AI and the convergence of data and model engineering: opportunit... von Paolo Missier
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...
Paolo Missier34 views
Perth MeetUp November 2023 von Michael Price
Perth MeetUp November 2023 Perth MeetUp November 2023
Perth MeetUp November 2023
Michael Price15 views
Architecting CX Measurement Frameworks and Ensuring CX Metrics are fit for Pu... von NUS-ISS
Architecting CX Measurement Frameworks and Ensuring CX Metrics are fit for Pu...Architecting CX Measurement Frameworks and Ensuring CX Metrics are fit for Pu...
Architecting CX Measurement Frameworks and Ensuring CX Metrics are fit for Pu...
NUS-ISS37 views
RADIUS-Omnichannel Interaction System von RADIUS
RADIUS-Omnichannel Interaction SystemRADIUS-Omnichannel Interaction System
RADIUS-Omnichannel Interaction System
RADIUS15 views

Deep learning - a primer