1. Introduction to Deep Learning with Keras

2. Machine Learning on Images
Given examples, can we train a computer to do:
Source -

3. Machine Learning on Images
Source -

4. Artificial Neural Networks
Signal goes in, via input layer
Weighted links transfer input values to neurons in hidden layers
Signals are summed at hidden neurons and passed through transfer/activation function
Processed signal arrives at output layer
Decisions made using output signal(s)

5. What’s in an (Artificial) Neuron?
Source -

6. More layers can encapsulate more knowledge
Why Deep Learning?
More layers can encapsulate more knowledge
More weights to train – need more data, need more computation

7. Weights encapsulate the knowledge of a network
Where’s the Knowledge?
Weights encapsulate the knowledge of a network
Network learns using an algorithm that optimize weights given examples
Back propagation is commonly used – learn weights from examples using
some linear algebra

8. Classification Example – MNIST
Which digit is it?

9. DEEP Different Classifiers on the MNIST Database Why Deep Learning?
Type
Classifier
Distortion
Preprocessing
Error rate (%)
Linear classifier
Pairwise linear classifier
None
Deskewing
7.6[9]
K-Nearest Neighbors
K-NN with non-linear deformation (P2DHMDM)
Shiftable edges
0.52[18]
Boosted Stumps
Product of stumps on Haar features
Haar features
0.87[19]
Non-linear classifier
40 PCA + quadratic classifier
3.3[9]
Support vector machine
Virtual SVM, deg-9 poly, 2-pixel jittered
0.56[20]
Neural network
2-layer
1.6[21]
elastic distortions
0.7[21]
Deep neural network
6-layer
0.35[22]
Convolutional neural network
6-layer
Expansion of the training data
0.31[15]
6-layer
0.27[16]
Committee of 35 CNNs, 1-20-P-40-P
Width normalizations
0.23[8]
Committee of 5 CNNs, 6-layer
0.21[17]
DEEP

10. Convolutional Neural Networks
Complex architectures, many layers – really good for image recognition tasks
Lots of computing power needed to do the training mathematics!

11. GPU cards are exceptionally well suited to Neural Network Mathematics
GPUs to the Rescue!
GPU cards are exceptionally well suited to Neural Network Mathematics
Orders of magnitude faster than CPU-based training

12. https://keras.io High-level, open-source Python API
“Being able to go from idea to result with the least possible delay is key to doing good research”
Interface for TensorFlow, Microsoft Cognitive Toolkit, and Theano

13. $ module load python/3.6.4-anaconda
Installing a Conda Environment for Keras and TensorFlow with Jupyter Support
$ module load python/3.6.4-anaconda
$ conda create --name py3.6-keras python=3.6 ipykernel keras tensorflow-gpu pillow matplotlib
$ ipython kernel install --user --name py3.6-tfgpu --display-name=“Keras (GPU)"