PYTHON

1. Introduction to Mathematics for Deep Learning
  1. Linear Algebra
  2. Partial Differentiation
  3. Statistics and Probability
  4. Information Theory
2. Introduction to Machine Learning (Practicals Included) -
  1. Introduction to Regression
  2. Introduction to Gradient Descent
  3. Support Vector Machines
  4. Decision Trees, Random Forest
  5. Introduction to Genetic Algorithm
3. Building Blocks of Neural Networks (Practicals Included)-
  1. The Image Classification Problem
  2. Loss Functions c. Regularization
  3. Optimization
  4. BackPropagation
  5. Common activation functions
  6. Xavier Initialization
  7. Dropouts
4. Introduction to Deep Learning tools (Hands On)-
  1. Pytorch
  2. Tensorflow
5. Computer Vision (Practicals Included)-

a. Components of ConvNets

   i. Conv Layer

   ii. Pooling Layer

   iii. Normalization Layer

   iv. Fully Connected Layers Conversion of Fully Connected layers to Conv Layers

   v. Conversion of Fully Connected layers to Conv Layers

b.  Problems with ConvNets

c. Different Architectures of CNNs

d. Implementing ConvNets

 

 

6. Introduction to some advanced Computer Vision algorithms like YOLO, Faster RCNNs etc.

a. Components of ConvNets

   i. Conv Layer

   ii. Pooling Layer

   iii. Normalization Layer

   iv. Fully Connected Layers Conversion of Fully Connected layers to Conv Layers

   v. Conversion of Fully Connected layers to Conv Layers

b.  Problems with ConvNets

c. Different Architectures of CNNs

d. Implementing ConvNets

 

 

7. Autoencoders and Variational Autoencoders (Practicals Included)

a. Components of ConvNets

   i. Conv Layer

   ii. Pooling Layer

   iii. Normalization Layer

   iv. Fully Connected Layers Conversion of Fully Connected layers to Conv Layers

   v. Conversion of Fully Connected layers to Conv Layers

b.  Problems with ConvNets

c. Different Architectures of CNNs

d. Implementing ConvNets

 

 

8. Introduction to Mathematics for Deep Learning -

a. Linear Algebra
b. Partial Differentiation
c. Statistics and Probability
d. Information Theory

9. Introduction to Machine Learning (Practicals Included) -

a. Introduction to Regression
b. Introduction to Gradient Descent
c. Support Vector Machines
d. Decision Trees, Random Forest
e. Introduction to Genetic Algorithm

10. Building Blocks of Neural Networks (Practicals Included)-

a. The Image Classification Problem
b. Loss Functions
c. Regularization
d. Optimization
e. BackPropagation
f. Common activation functions
g. Xavier Initialization
h. Dropouts

11. Introduction to Deep Learning tools (Hands On)-

a. Pytorch
b. Tensorflow

12. Visualizing Neural Networks
13. Introduction to NLP (Practicals Included)

a. Word2Vec and Glove
b. Topic Modelling
c. Deep-learning-free Text and Sentence Embedding
d. Question Generation

14. Introduction to Recurrent Neural Networks (Practicals Included)

a. LSTM and its variants
b. Attention and Variational Attention
c. Implementing LSTM in any chosen frameworks

15. Introduction to GANs (Practicals Included)
16. Introduction to Reinforcement Learning (Practicals Included)-

a. Introduction to Autoencoders and Variational Autoencoders
b. Formulating a reinforcement learning problem
c. Various Reinforcement Learning Algorithms
e. Implementation in OpenAI gym