Introduction
•Course resources
•Setting Up R Studio and R crash course
•Installing R and R studio
•Basics of R and R studio
•Packages in R
•Inputting data part 1: Inbuilt datasets of R
•Inputting data part 2: Manual data entry
•Inputting data part 3: Importing from CSV or Text files
•Creating Barplots in R
•Creating Histograms in R
•Single Cells – Perceptron and Sigmoid Neuron
•Perceptron
•Activation Functions
•Neural Networks – Stacking cells to create network
•Basic Terminologies
•Gradient Descent
•Back Propagation
•Some Important Concepts
•Standard Model Parameters
•Hyperparameters
•Tensorflow and Keras
•Keras and Tensorflow
•Installing Keras and Tensorflow
•R – Dataset for classification problem
•Data Normalization and Test-Train Split
•R – Building and training the Model
•Building, Compiling and Training
•Evaluating and Predicting
•The NeuralNets Package
•ANN with NeuralNets Package
•Saving and Restoring Models
•Saving – Restoring Models and Using Callbacks
•Hyperparameter Tuning
•CNN – Basics
•CNN Introduction
•Stride
•Padding
•Filters and Feature maps
•Channels
•PoolingLayer
•Creating CNN model in R
•CNN on MNIST Fashion Dataset – Model Architecture
•Data Preprocessing
•Creating Model Architecture
•Compiling and training
•Model Performance
•Analyzing impact of Pooling layer
•Comparison – Pooling vs Without Pooling in R
•Project : Creating CNN model from scratch
•Project – Introduction
•Data for the project
•Project in R – Data Preprocessing
•CNN Project in R – Structure and Compile
•Project in R – Training
•Project in R – Model Performance
•Project : Data Augmentation for avoiding overfitting
•Project in R – Data Augmentation
•Project in R – Validation Performance
•Transfer Learning : Basics
•ILSVRC
•LeNET
•VGG16NET
•GoogLeNet
•Transfer Learning
•Transfer Learning in R
•Project – Transfer Learning – VGG16 (Implementation)
•