# Deep learning with TensorFlow Python

• ## Online & Offline

Sale Date Ended

INR 12000
Sold Out

Page Views : 90

## COURSE DESCRIPTION

TensorFlow is a famous deep learning framework, this library is based on Python and will help you to run various algorithms of Artificial Neural network. Prerequisite: Participants must have knowledge of Python, knowledge of Machine learning will be helpful.

## OBJECTIVE

Introductory Terms

• Data and Data Science.
• Big Data.
• Why Big Data.
• Math and Data Science.
• Introduction to Statistics.
• What is learning?
• Different type of learning.
• Introduction to Data mining, machine learning.
• Introduction to artificial intelligence.
• What is a model?
• Mathematical models.

NumPy Refresher :

• Introduction to NumPy.
• Ndarray.
• Array creation
• Matrix
• addition, subtraction, multiplication on Array
• Matrix multiplication.

MatPlotlib Refresher

• Pyplot as submodule.
• Scatterplot
• lineplot
• histogram
• PiChart
• Bar Chart

Pandas Refresher

• DataFrame
• Dataframe operations

TensorFlow Introduction

• TensorFlow History.
• Installing TensorFlow.
• Introduction to Jupyter.
• TensorFlow with Jupyter.
• Introduction to tensor in context of tensor flow.
• TensorFlow Data types
• Computation and Dataflow graph
• Concept of session.
• Constant
• Placeholder
• Variables.

Mathematical operations in TensorFlow

• Multiplication
• Summation
• Maximum
• Minimum
• Complex number operations.
• Some more mathematical functions.

Matrix operation and Linear algebra in TensorFlow

• Matrix summation and Substraction.
• Matrix Transpose.
• Determinant of Matrix.
• Matrix multiplication.
• Inverse matrix.

Linear regression

• Introduction to linear regression.
• Simple linear regression.
• Parameter estimations.
• Simple linear regression with TensorFlow.
• Evaluating our model.

Logistic Regression

• Logistic Regression Introduction.
• Parameter estimation.
• With TensorFlow.
• Model Evaluation.

Clustering

• Introduction to Clustering
• Kmeans
• Kmeans with TensorFlow
• Optimizing Kmeans
• Market Segmentation.

Deep Learning

• Introduction
• Use cases
• Why I use deep learning ?

Introduction to Neural Network

• Biological Neuron an Introduction.
• Component of biological Neuron.
• Artificial Neuron.
• Working of artificial neuron.
• Activation function

◦ Sigmoid function.

◦  Linear

◦  ReLU

◦  Tanh

• Concept of feed forward.
• AND, OR and NOT
• Perceptron.
• Perceptron learning algorithm.
• Implementing Perceptron in TensorFlow.

Multilayer perceptron

• Backpropgation algorithm.
• MLP with TensorFlow.
• Classifying our data.

Convolutional  Neural networks (CNN)

• Convolutional Neural networks Introduction.
• Convolutional Layer.
• Pooling Layer .
• Connecting fully.
• Image classification and Convolutional Networks.
• TensorFlow and CNN
• Image Classification with TensorFlow.
• Model evaluation

Recurrent Neural network (RNN)

• Introduction
• Back Propagation through time (BPTT)
• Need of Memory.
• Long Short Term memory (LSTM).
• Bi-Directional RNN
• Word embeding
• Implementing RNN with TensorFlow.
• Time Series and RNN
• Sequence prediction with RNN.

Projects :

• Three Projects on Image classifications
• One Project on time series with RNN
• One Project on sequence prediction