Machine Learning Workshop
Anthill Inside 2017
- Recent Graduate from Delhi Technological University
- B.Tech in Mathematics and Computing Engineering
- Machine Learning Instructor at Coding Blocks.
- Research Intern at IIIT-D
- Supervised by Dr. Ganesh Bagler
- Working on drug-side-efffect predictions
- A few papers (accepted and under-review) on Evolutionary Optimization, Vision and ML.
- Independent Study on Deep Learning, Reinforcement Learning.
- Introduction to Machine Learning
- Four Sessions (~90 mins each)
- Mathematical Conceptualisation
- Project Implementation
- Introduction and warm-up
- CNN architectures and applications
- Transfer Learning & Sequence Processing
- Reinforcement Learning
Session 01: Introduction
- History and Introduction to DL
- Applications (Industrial and daily)
- Convex Optimization
- Hands-on with code
- Introduction and some History
- The Gartner Hype Cycle
- Image classification/recognnition
- Image captioning/VQA
- Sequence processing
- Speech Recognition
A brief discussion
Relation with Logistic Regression
Neurons and ANN
Artificial Neural Network
(Chain rule for neural nets)
What's going on inside the black box?
Neural Nets as Feature extractors
It's all about Manifolds
Every layer is a transformation operation
Some examples of transformation operations
Build your own neural network
Libraries: Numpy, Matplotlib
Some Popular Frameworks
- And more...
What is Convolution?
Padding, Strides etc...
Application to Neural Networks
Advantages and Disadvantages over ANN
Hands-on with CNNs
The MNIST dataset
How it works?
Some visualizations of filters
models like VGG, AlexNet, Inception-v3 etc.
Using Pre-trained models
Use VGG-19 from Keras
Session 03: Transfer Learning
- What is it?
Small Demo with MNIST
with VGG-16/19 Net
Results and Discussion
- Accuracy and Loss
- Training Time
Deep Dream and Style Transfer
Let's build both!
Introduction to Recurrent Architectures
The Recurrent Neural Network
Training of RNN
Backprop through time
Improvements over RNN
Long Short-Term Memory (LSTM)
and thought-vector representations
Music generation with LSTMs
Applications of Previous Concepts
- AutoEncoder models
- Sequence to sequence learning
- Neural Machine Translation
- Sentiment classification
- And more...
Session 04: Reinforcement Learning
- Supervised, Unsupervised and RL
- Learning through Rewards
- The algorithm powering AlphaGo
- A Dynamic Programming approach
- Update function
- Toy task with simple graph
- Feature based learning
- Approximate rewards
- Basis for Deep Q-Networks
and solving Atari games
- Game-play understanding
- The Reward function
- DQN on Atari Ms-Pacman
- Hands-on project
Train Flappy bird with RL
- Some more examples
- What to do after the workshop
- Resources and papers to follow
Deep Learning Applications: A hands-on approach
By Shubham Dokania