1. Calculus Essentials – Derivatives, Limits, Integral calculus, calculus in Neural Network
2. Introduction to TensorFlow and Keras
3. Perceptrons: Understanding the concept of perceptrons
4. Activation Functions & Loss Functions
5. Artificial Neural Networks: Introduction to Perceptron rule and Gradient Descent rule
6. Gradient Descent and Backpropagation:
7. Optimization, Drop outs and Regularization parameters: Concepts of Overfitting and
capacity, Cross validation, Features selection, regularization and hyperparameters
8. Convolutional Neural Networks: Intro to CNN kernel filter, principles, behind CNNs,
Multiple filters and CNN application
9. Recurrent Neural Networks: Intro to RNNs, Unfolded RNNs, LSTM, and RNN application
10. Deep Learning applications: How to conduct image processing, Natural Language
Processing, Speech Recognition, and Video Analytics
11. Natural language processing
11.1. Text Extraction techniques
11.2. Bag of words, TF-IDF, N-Grams
11.3. Word2vec, GLOVE
11.4. RNN
11.5. LSTM
11.6. Sentiment analysis
11.7. Machine translation
12. Computer vision
12.1. Pre-processing Image Data
12.2. Convolutional Neural Networks
12.3. Transfer Learning – ResNet, AlexNet, VGGNet, InceptionNet.
12.4. Keras library for CNNs
13. Reinforcement learning
13.1. Value-based methods (e.g. Q-learning)
13.2. Policy-based methods
