CURRICULUM

1. Python basics

This module will be a crash course in Python for those that are unfamiliar with the language. If you have experience in Python, it will serve as a short refresher.

  1. Intro to interpreted languages
  2. Hello world in python
  3. Variables and data types
  4. Functions
  5. Control flow
  6. List comprehension
  7. Classes
  8. Files
2. Numpy and ND arrays
  1. Python Libraries
  2. Array creation and representation
  3. Indexing and slicing
  4. Universal Functions
  5. Reductions
  6. Linear operations
  7. Data visualization in Python
3. Deep learning 101
  1. Deep Learning, Machine Learning and Artificial Intelligence Programming Basics
  2. Fundamentals of deep learning
  3. Building neural network from scratch (how to program them)
4. Creating Models in Keras
  1. Intro to Machine Learning libraries
  2. Keras layers and models
  3. Optimizers and loss functions
  4. Training a Keras model
5. Introduction to Convolutional Neural Networks (ConvNets )
  1. Real World uses of Convnet
  2. What is convolution?
  3. Convolution in image processing
      Kernels
      Stride
      Padding
      Pooling
6. Training a Convnet in Keras
  1. Building a convnet using keras
  2. Training the convnet on MNIST dataset
  3. Plotting the loss graph in matplotlib
7. Convnet Architectures
  1. Concept
  2. AlexNet
  3. VGG
  4. GoogleNet
  5. Darknet
  6. Resnet
8. Common Application Algorithms with Convnet
  1. Classification
  2. Object Detection
  3. Object Segmentation
  4. Example – Classification and detection using YOLO (darknet)
  5. Deep Learning for text and Sequences
9. Understanding sequential data and the concept of Recurrent Neural Networks in the context of Sequential data
  1. What is Sequential data
  2. What is RNN and why is it used?
  3. Forward Propagation
  4. Backprop through time
10. Understand different architectures of RNN
  1. One – one
  2. Many – Many
  3. Many – one
  4. One – Many
  5. idirectional
  6. Encoder – Decoder
  7. LSTM
  8. GRU
  9. Attention model
11. Learn to implement a RNN in keras for different applications
  1. RNN for NLP
  2. Machine Translation
  3. Sentiment Classification
  4. Named Entity Recognition