Only Few Seats Left

Module

1

·       Basics of Python: Objects and Data Types

·       Numpy Basics: Arrays, Index Selection and Operations

·       Pandas Basics: Series, DataFrames, Group By and other Pandas Operations

·       Python for Data visualization & plotting using libraries like Matplotlib & Seaborn

·       PyTorch and Tensor Basics and Operations

·       Machine Learning Basics, introduction to supervised & unsupervised learning

Module

2

·       Linear Regression for One & Multiple Variables

·       Ordinary Least Square, Dummy Variables, One Hot Encoding, Polynomial Regression

·       Anscombe’s quartet, Performance Metrics like Mean Absolute Error, Root Mean Squared Error

·       Logistic Regression, Sigmoid Function, Anscombe’s quartet

·       Confusion Matrix, interpreting parameters like F-1 score, Accuracy, Precision, Recall etc. 

Module

3

·       Introduction to Deep Learning

·       Artificial Neural Networks

·       Perceptron Model, Activation Functions

·       Forward and Backward Propagation

·       Bias-variance trade off, Overfitting & Underfitting of Deep Learning Models

·       Discussion on Keras and TensorFlow

Module

4

·       Cost Functions and Gradient Descent

·       Convolutional Neural Networks, Pooling

·       Layers, Convolutional Layers

·       Convolutional Neural Networks, Image Kernels and Filters,

·       Convolutions, Pooling Layers, convolution kernels

·       Local connectivity, Pooling/Down sampling Layer

Module

5

·       Max Pooling, Dropout Technique, AlexNet

·       Recurrent Neural Networks, Sequential Information, Recurrent Neurons, “Unrolled” layer.

·       Sequence to Sequence, Sequence to Vector, Vector to Sequence, Exploding Gradients, Vanishing Gradient

·       Long Short-Term Memory (LSTM) networks, RNN on a Sine Wave

·       Multivariate Time Series with LSTM RNN

Module

6

·       Natural Language Processing with Deep Learning: Embedding Layer,

·       Gated Recurrent Unit, Dense

·       Text Vectorization and Encoding Dictionary

·       Autoencoders: Dimensionality Reduction and Noise Removal

·       Generative Adversarial Networks (GANs): Generators and Discriminators, Deep Convolutional GANs (DCGANs)