Page 102 - B.E CSE Curriculum and Syllabus R2017 - REC
P. 102
Department of CSE, REC
REFERENCES:
1. Stefan Buttcher, Charles L. A. Clarke, Gordon V. Cormack, Information Retrieval Implementing and
Evaluating Search Engines, The MIT Press, Cambridge, Massachusetts London, England, 2010
2. http://www.search-engines-book.com/slides/.
CS17E84 DEEP LEARNING L T P C
3 0 0 3
OBJECTIVES:
To acquire knowledge on the basics of neural networks.
To implement neural networks using computational tools for variety of problems.
To explore various deep learning algorithms.
To implement Neural Networks using Tensorflow.
To know the various applications of Deep Learning.
UNIT I CONVOLUTIONAL NEURAL NETWORKS 9
Neurons in Human Vision-The Shortcomings of Feature Selection-Vanilla Deep Neural Networks Don’t
Scale-Filters and Feature Maps-Full Description of the Convolutional Layer-Max Pooling-Full Architectural
Description of Convolution Networks-Closing the Loop on MNIST with Convolutional Networks-Image
Preprocessing Pipelines Enable More Robust Models-Accelerating Training with Batch Normalization-
Building a Convolutional Network for CIFAR10-Visualizing Learning in Convolutional Networks -
Leveraging Convolutional Filters to Replicate Artistic Styles-Learning Convolutional Filters for Other
Problem Domains.
UNIT II MEMORY AUGMENTED NEURAL NETWORKS 9
Neural Turing Machines-Attention-Based Memory Access-NTM Memory Addressing Mechanisms-
Differentiable Neural Computers-Interference-Free Writing in DNCs-DNC Memory Reuse-Temporal Linking
of DNC Writes-Understanding the DNC Read Head-The DNC Controller NetworkVisualizing the DNC in
Action-Implementing the DNC in TensorFlow-Teaching a DNC to Read and Comprehend.
UNIT III DEEP REINFORCEMENT LEARNING 9
Deep Reinforcement Learning Masters Atari Games - Reinforcement Learning -Markov Decision Processes
(MDP)-Explore Versus Exploit-Policy versus Value Learning-Pole-Cart with Policy Gradients-Q-Learning
and Deep Q-Networks-Improving and Moving Beyond DQN.
UNIT IV IMPLEMENTING NEURAL NETWORKS IN TENSORFLOW 9
Introduction to TensorFlow – Comparitive analysis of Tenforflow - Installing TensorFlow-Creating and
Manipulating TensorFlow Variables-TensorFlow Operations-Placeholder Tensors-Sessions in TensorFlow-
Navigating Variable Scopes and Sharing Variables-Managing Models over the CPU and GPU-Specifying the
Logistic Regression Model in TensorFlow-Logging and Training the Logistic Regression Model-Leveraging
TensorBoard to Visualize Computation Graphs and Learning-Building a Multilayer Model for MNIST in
TensorFlow.
UNIT V APPLICATIONS OF DEEP LEARNING 9
Deep learning for computer vision – Data Augmentation - Neural Language Models - High-Dimensional
Outputs – Health care applications.
TOTAL: 45 PERIODS
OUTCOMES:
At the end of the course, student will be able to:
Develop algorithms simulating human brain.
Implement Neural Networks in Tensor Flow for solving problems.
Explore the essentials of Deep Learning and Deep Network architectures.
Apply reinforcement
Define, train and use a Deep Neural Network for solving real world problems that require artificial
Intelligence based solutions.
Curriculum and Syllabus | B.E. Computer Science and Engineering | R2017 Page 102

