Deep Learning (from basics)

The video gently introduces AI - ML- DL and then takes you to what's "deep" in deep learning, what's "learning" in Deep Learning and ends with what are next activities. In the end, the video gives the course overview which will get covered in next videos.

The video describes what is a Tensor and what are various sensor types.

This video shows hands-on Implementation about tensors.

Lab: Perform the hands-on implementation that is demonstrated in the video  (by doing coding).

The video describes various tensor operations. It also shows hands-on Implementation of these tensor operations

Lab: Perform the implementation shown in the video (by doing coding)

The video first describes in brief what is Tensor Flow, how it is related to Keras.

The video introduces important aspects of Keras.

The video introduces what is Artificial Neural Network (ANN). Meaning of Layers in ANN. It also gives overview of Back Propagation approach in ANN.

This video covers optimizer - brief information about Adam optimizer.

The video also covers various Activation Functions.  Working of RELU is also demonstrated as part of Activation Function.

Lab: Perform the demonstration covered in this video (by doing coding).

This video talks about various Loss functions used in Deep Learning. It also suggests applicability of loss function in various scenarios

This video talks about installation required for using Keras.

It describes Keras workflow. It also describes an hands-on experiment using Keras.

This video gives hands-on implementation of Keras for image classification.

Lab: Perform the hands-on implementation (by doing coding)

This video talks about details of Convolutional Neural Network.

- what is convolution,

- Pooling concept,

- layer requirements,

- CNN structure

It also talks about applying CNN to image data sets and doing it hands-on

This video shows hands-on Implementation of CNN using large Image data sets.

Lab: Perform the hands-on implementation (by doing coding)

This video shows hands-on Implementation of CNN using large Image data sets.

Lab: Perform the hands-on implementation (by doing coding)

This video talks about Text Sequences and techniques for handling text sequences.

It talks about word embeddings and its use for movie reviews classification.

This video gives hands-on implementation of word embeddings technique for handling text sequences.

It makes of pretrained word embedding model and classifies movie reviews comments positive or negative.

Lab: Perform the hands-on implementation (by doing coding)

This video talks about what is Recurrent Neural Network, the concepts behind RNN and support in Keras for RNN.

This video gives implementation  of RNN.

It also gives how to use RNN support of Keras with an example.

Lab: Perform the hands-on implementation (by doing coding)

This video talks about LSTM , concept behind LSTM and then graduate towards Bidirectional RNN. The concept behind Bidirectional RNNs is also explained.

This video provides hands-on implementation of using LSTM support in keras for text analysis.

Lab: Perform the hands-on implementation (by doing coding)

This video gives Bidirectional RNN implementation with Keras.

It also tells how reversed implementation can be done using LSTM. It gives implementation for Bidirectional RNNs (LSTM, GRU).

Lab: Perform the hands-on implementation (by doing coding)

The video explains the concept of Overfitting and Underfitting with Deep Learning model, what are the techniques to deal with it including dropouts.

Lab: The techniques explained in the video can be implemented (by doing coding)

This video talks about: -

• Overview of gradient descent,

• Mathematics of differentiation, gradients,

• Mathematics of functions with vector values, matrices

• Chaining derivatives

• Back propagation ,

• Chaining derivatives example calculations

This video talks about: -

• Overview of gradient descent,

• Mathematics of differentiation, gradients,

• Mathematics of functions with vector values, matrices

• Chaining derivatives

• Back propagation ,

• Chaining derivatives example calculations