JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD

Course Objectives

students will be able

• 1. To understand complexity of Deep Learning algorithms and their limitations
• 2. To be capable of performing experiments in Deep Learning using real-world data.

Course Outcomes:

• 1. Implement deep learning algorithms, understand neural networks and traverse the layers of data
• 2. Learn topics such as convolutional neural networks, recurrent neural networks, training deep networks and high-level interfaces
• 3. Understand applications of Deep Learning to Computer Vision
• 4. Understand and analyze Applications of Deep Learning to NLP

UNIT - I

Introduction: Feed forward Neural networks, Gradient descent and the back propagation algorithm, Unit saturation, the vanishing gradient problem, and ways to mitigate it. RelU Heuristics for avoiding bad local minima, Heuristics for faster training, Nestors accelerated gradient descent, Regularization, Dropout

UNIT - II

Convolutional Neural Networks: Architectures, convolution/pooling layers, Recurrent Neural Networks: LSTM, GRU, Encoder Decoder architectures. Deep Unsupervised Learning: Auto encoders, Variational Auto-encoders, Adversarial Generative Networks, Auto-encoder and DBM Attention and memory models, Dynamic Memory Models

UNIT - III

Applications of Deep Learning to Computer Vision: Image segmentation, object detection, automatic image captioning, Image generation with Generative adversarial networks, video to text with LSTM models, Attention Models for computer vision tasks

UNIT - IV

Applications of Deep Learning to NLP: Introduction to NLP and Vector Space Model of Semantics, Word Vector Representations: Continuous Skip-Gram Model, Continuous Bag-of-Wordsmodel (CBOW), Glove, Evaluations and Applications in word similarity

UNIT - V

Analogy reasoning: Named Entity Recognition, Opinion Mining using Recurrent Neural Networks: Parsing and Sentiment Analysis using Recursive Neural Networks: Sentence Classification using Convolutional Neural Networks, Dialogue Generation with LSTMs

TEXT BOOKS:

• 1. Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press.
• 2. The Elements of Statistical Learning by T. Hastie, R. Tibshirani, and J. Friedman, Springer.
• 3. Probabilistic Graphical Models. Koller, and N. Friedman, MIT Press.

REFERENCES:

• 1. Bishop, C, M., Pattern Recognition and Machine Learning, Springer, 2006.
• 2. Yegnanarayana, B., Artificial Neural Networks PHI Learning Pvt. Ltd, 2009.
• 3. Golub, G.,H., and Van Loan,C.,F., Matrix Computations, JHU Press,2013.
• 4. Satish Kumar, Neural Networks: A Classroom Approach, Tata McGraw-Hill Education, 2004.