Applications of Deep Learning

To develop a working knowledge of various deep learning algorithms

To learn implementation aspects of DL algorithms for various machine learning problems with applications to spatial and temporal datasets

• Formulate a supervised deep learning problem

• To implement a suitable DL algorithm for real-world data

• Design and code suitable DL architectures

• To implement and evaluate the performance of DL algorithms on real-world datasets

1. Introduction

Review of machine Learning basics, review of artificial neural networks

2. Convolutional Networks and Optimization

Motivation, Pooling, Convolution algorithms, Optimization techniques, Gradient descent, Batch optimization

3. Sequence Modeling and Generative models

Recurrent neural networks, LSTMs, Bi-LSTMs, Auto-encoders

4. Effective training

Early stopping, Dropout, and Normalization methods

5. Standard applications

Computer vision, Speech processing

6. DL for signal analysis

1D - convolutional networks, Hybrid architectures, Bio-signal analysis

Main Textbooks

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.

References

Gulli, A., Kapoor, A., & Pal, S. (2019). Deep learning with TensorFlow 2 and Keras: regression, ConvNets, GANs, RNNs, NLP, and more with TensorFlow 2 and the Keras API. Packt Publishing Ltd.

Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. " O'Reilly Media, Inc.".

Trask, A. W. (2019). Grokking deep learning. Simon and Schuster.