UNIT I The Neural Network [12 Hours]
Building Intelligent Machines – The Limits of Traditional Computer Programs – The Mechanics of Machine Learning – The Neuron – Expressing Linear Perceptrons as Neurons – Feed-Forward Neural Networks – Linear Neurons and Their Limitations -Sigmoid, Tanh, and ReLU Neurons – Training Feed-Forward Neural Networks: The Fast-Food Problem – Gradient Descent – The Delta Rule and Learning Rates – Gradient Descent with Sigmoidal Neurons – The Backpropagation Algorithm – Test Sets, Validation Sets, and Overfitting – Preventing Overfitting in Deep Neural Networks
UNIT II Implementing Neural Networks in TensorFlow [12 Hours]
What Is TensorFlow? – How Does TensorFlow Compare to Alternatives? – Installing TensorFlow – Creating and Manipulating TensorFlow Variables – TensorFlow Operations – Placeholder Tensors – Sessions in TensorFlow – Beyond Gradient Descent: The Challenges with Gradient Descent – Local Minima in the Error Surfaces of Deep Networks – Model Identifiability – Momentum-Based Optimization – A Brief View of Second-Order Methods – Learning Rate Adaptation
UNIT III Convolutional Neural Networks [12 Hours]
Neurons in Human Vision – The Shortcomings of Feature Selection – Filters and Feature Maps – Max Pooling – Full Architectural Description of Convolution Networks – Accelerating Training with Batch Normalization – Building a Convolutional Network for CIFAR-10 – Visualizing Learning in Convolutional Networks – Embedding and Representation Learning: Learning Lower-Dimensional Representations – Principal Component Analysis – Motivating the Autoencoder Architecture – Implementing an Autoencoder in TensorFlow
UNIT IV Introduction to AI & ML [12 Hours]
What is Artificial Intelligence? – The Turing Test – Heuristics – Knowledge Representation – Expert Systems – Major Parts of AI – Introduction to Machine Learning: What is Machine Learning? – Types of Machine Learning Algorithms – Feature Engineering, Selection and Extraction – Dimensionality Reduction – Working with Datasets – The Bias-Variance Tradeoff
UNIT V Deep Learning AI [12 Hours]
Keras and the XOR function – What is Deep Learning? – What are Perceptrons? – The Anatomy of an Artificial Neural Network – The Loss Function Hyperparameter – The Optimizer Hyperparameter – What is Backward Error Propagation? – What is a Multi-Layer Perceptron? – The Convolutional Layer – The ReLU Activation Function – Deep Learning: RNNs and LSTMs: What is an RNN? – What Is an LSTM? – Working with Tensorflow and LSTM
TEXT(S)
- Nikhil Buduma, “Fundamentals of Deep Learning – Designing Next-Generation Machine Intelligence Algorithms”, O’Reilly, 2017, First Edition, ISBN: 978-1-491-92561-4
- Oswald Campesato, “Artificial Intelligence Machine Learning and Deep Learning”, Mercury Learning and Information, 2020, ISBN: 978-1-68392-467-8
REFERENCE MATERIALS
- Goodfellow, I, Bengio,Y, and Courville, A, “Deep Learning”, MIT Press, 2016.
- Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola, “Dive into Deep Learning – Release 0.17.0”, Amazon Science, First Edition, 2021, ISBN 1544361378