01Week 1: Python Basics for Data Science
Day 1: Python Basics for Data Science
- Introduction to Google Colab
- Data Types and Typecasting
- Conditionals, and Loops
Day 2: Python Basics for Data Science
- List Comprehensions
- Functions, and Lambda Functions
- Randomization
- Inputs in Python
02Week 2: Feedforward Neural Networks
Day 1: Feedforward Neural Networks
- Understanding the AI Glossary
- Perceptron, and Activation Functions
- Layers and MLPs
- Understanding the Training Loop
Day 2: Backpropagation
- Backpropagation by Hand
- Loss and Error Metrics
- Project: MNIST Handwritten Digits Classification
03Week 3: More Neural Networks
Day 1: Convolutional Neural Networks
- What is an image?
- Understanding kernels and convolutions
- Convolution Layers, Pooling Layers
- Convolutional Neural Networks
- Project: Cats vs Dogs Classification
Day 2: Understanding the Intuition of Recurrent Neural Networks
- What is a Sequence?
- What is a Seq2Seq Model?
- The RNN Cell
- The LSTM Cell
- Long-term Dependencies: Why RNNs are no longer relevant
04Week 4: Transformers - Conceptuals
Day 1: Transformers - Conceptual Knowledge
- Seq2Seq Models with RNN
- What is Attention?
- A High-Level Look at Transformers
- Encoders
- Self-Attention
Day 2: Transformers - Conceptual Knowledge
- How are Attention Scores calculated?
- Multi-Headed Attention
- Positional Encoding
- Residuals & Layer Normalization
- Decoders
- Linear and Softmax Layer
- Revisiting the High-Level Look