2. Introduction
• AI - simulation of human intelligence in machines that are programed
to think like humans and mimic their actions
• ML
• The field of study that gives computers the ability to learn without being
explicitly programmed
• DL-broader family of machine learning methods based on artificial
neural networks with representation learning
• DM vs ML
• data mining - “extracting information from data.
• ML – algorithms used during data mining for acquiring the structural
descriptions from the raw data
7/23/2020 Introduction to Deep Learning 2
9. Neural Network vs Deep Learning
7/23/2020 Introduction to Deep Learning 9
10. Deep learning
Definition: neural networks with a large number of parameters and layers in
one of four fundamental network architectures:
• Unsupervised pretrained networks
• Convolutional neural networks
• Recurrent neural networks
• Recursive neural networks
• Advantages
• Automatic feature extraction is one of the great advantages that deep learning has
over traditional machine learning algorithms
• surpassed those conventional algorithms in accuracy for almost every data type with
minimal tuning and human effort
• help data science teams save their blood, sweat, and tears for more meaningful
tasks.
7/23/2020 Introduction to Deep Learning 10
11. Applying machine learning
• best understood by asking the correct questions to begin with
• What is the input data from which we want to extract information (model)?
• What kind of model is most appropriate for this data?
• What kind of answer would we like to elicit from new data based on this
model?
7/23/2020 Introduction to Deep Learning 11
12. References
1. Josh Patterson and Adam Gibson, “Deep Learning – A
Practitioner’s Approach”, First Edition, O’Reilly Series,
August-2017
2. Ian Goodfellow ,Yoshua Bengio and Aaron Courville, “Deep
Learning”, First Edition, MIT Press, 2016
7/23/2020 Introduction to Deep Learning 12