01/

INTRO TO DEEP LEARNING CONCEPTS

• INTRO TO DEEP LEARNING

• COMPUTATION GRAPH

02/

INTRO TO PYTORCH

• CODING WITH PYTORCH

03/

BASIC NEURAL NETWORKS

• NEURAL NETWORK REPRESENTATION

• ACTIVATION FUNCTIONS 

• DERIVATIVES

• GRADIENT DESCENT

• BACK PROPAGATION

• RANDOM INITIALIZATION

04/

DEEP NEURAL NETWORKS

• DEEP NEURAL NETWORKS

• FORWARD PROPAGATION

• BUILDING BLOCKS OF NEURAL NETWORK FORWARD AND BACKWARD PROPAGATION

• PARAMETERS VS HYPER PARAMETERS  REGULARIZATION

• DROPOUT

05/

TESTING YOUR NEURAL NETWORKS

• APPLIED DEEP LEARNING  NORMALIZATION

• WEIGHT INITIALIZATION

• NUMERICAL APPROXIMATION  GRADIENT CHECKING

• OPTIMIZATION ALGORITHMS

06/

OPTIMIZATION ALGOS

• GRADIENT DESCENT

•  WEIGHTED AND AVERAGE GRADIENT DESCENT

• MOMENTUM

•  RMSPROP

• ADAM

•  LEARNING RATE DECAY
• HYPERPARAMETER TUNING

• BATCH NORMALIZATION

• SOFTMAX REGRESSION CLASSIFIER

07/

CONVOLUTION NEURAL NETWORKS (CNN)

• FOUNDATION OF CNN 

• PADDING 

• CONVOLUTIONS 

• POOLING 

• EXAMPLES

08/

FAMOUS NEURAL NETWORK CNN ARCHITECTURES

• ALEXNET 

• RESNET 

• MOBILENET 

• U-NET 

• INCEPTION

09/

APPLICATIONS OF CNN

• TRANSFER LEARNING 

• DATA AUGMENTATION 

• OBJECT LOCALIZATION 

• LANDMARK DETECTION 

• OBJECT DETECTION 

• BOUNDING BOX PREDICTION 

• ANCHOR BOX 

• YOLO 

• FACE RECOGNITION 

• NEURAL STYLE TRANSFER

10/

SEQUENCE MODELS IN DEEP LEARNING

• SEQUENCE MODELS 

• NOTATION 

• RECURRENT NEURAL NETWORKS 

• BACK PROPAGATION WITH TIME 

• PROBLEMS WITH RNN 

• LSTM NETWORKS 

• GRU NETWORKS 

• TRANSFORMER NETWORKS 

• BEAM SEARCH 

• TRIGGER WORD DETECTION 

• SPEECH RECOGNITION 

• BERT MODEL

11/

DEEP NEURAL NETWORKS

• DEEP NEURAL NETWORKS

• FORWARD PROPAGATION 

• BUILDING BLOCKS OF NEURAL NETWORK 

• FORWARD AND BACKWARD 

• PROPAGATION 

• PARAMETERS VS HYPER PARAMETERS 

• REGULARIZATION 

• DROPOUT