Learn Deep Learning Applications Development with Tensor Flow

Duration: Hours

Training Mode: Online


TensorFlow is an open-source library developed by Google primarily for deep learning applications. It also supports traditional machine learning. TensorFlow was originally developed for large numerical computations without keeping deep learning in mind.

1. Introduction To Deep Learning

a). Deep Learning: A revolution in Artificial Intelligence

b). Limitations of Machine Learning

c). Discuss the idea behind Deep Learning

d). Advantage of Deep Learning over Machine learning

e). 3 Reasons to go Deep

f). Real-Life use cases of Deep Learning

g). Scenarios where Deep Learning is applicable

The Math behind Machine Learning: Linear Algebra

a). Scalars

b). Vectors

c). Matrices

d). Tensors

e). Hyper planes

The Math Behind Machine Learning: Statistics

a). Probability

b). Conditional Probabilities

c). Posterior Probability

d). Distributions

e). Samples vs Population

f). Resampling Methods

g). Selection Bias

h). Likelihood

Review of Machine Learning Algorithms

a). Regression

b). Classification

c). Clustering

2. Reinforcement Learning

a). Underfitting and Overfitting

b). Optimization

c). Convex Optimization

3. Fundamentals Of Neural Networks

a). Defining Neural Networks

b). The Biological Neuron

c). The Perceptron

d). Multi-Layer Feed-Forward Networks

e). Training Neural Networks

f). Backpropagation Learning

g). Gradient Descent

h). Stochastic Gradient Descent

i). Quasi-Newton Optimization Methods

j). Generative vs Discriminative Models

Activation Functions

a). Linear

b). Sigmoid

c). Tanh

d). Hard Tanh

e). Softmax

f). Rectified Linear

g). Loss Functions

h). Loss Function Notation

i). Loss Functions for Regression

j). Loss Functions for Classification

k). Loss Functions for Reconstruction

l). Hyperparameters

m). Learning Rate

n). Regularization

o). Momentum

p). Sparsity

4. Fundamentals Of Deep Networks

a). Defining Deep Learning

b). Defining Deep Networks

c). Common Architectural Principals of Deep Networks

d). Reinforcement Learning application in Deep Networks

e). Parameters

f). Layers

g). Activation Functions – Sigmoid, Tanh, ReLU

h). Loss Functions

i). Optimization Algorithms

j). Hyperparameters

k). Summary

5. Introduction To TensorFlow

a). What is TensorFlow?

b). Use of TensorFlow in Deep Learning

c). Working of TensorFlow

d). How to install Tensorflow

e). HelloWorld with TensorFlow

f). Running a Machine learning algorithms on TensorFlow

6. Convolutional Neural Networks (CNN)

a). Introduction to CNNs

b). CNNs Application

c). Architecture of a CNN

d). Convolution and Pooling layers in a CNN

e). Understanding and visualizing a CNN

f). Transfer Learning and Fine-tuning Convolutional Neural Networks

7. Recurrent Neural Networks (RNN)

a). Introduction to RNN Model

b). Application use cases of RNN

c). Modelling sequences

d). Training RNNs with Backpropagation

e). Long Short-Term memory (LSTM)

f). Recursive Neural Tensor Network Theory

g). Recurrent Neural Network Model

8. Restricted Boltzmann Machine (RBM) And Autoencoders

a). Restricted Boltzmann Machine

b). Applications of RBM

c). Collaborative Filtering with RBM

d). Introduction to Autoencoders

e). Autoencoders applications

f). Understanding Autoencoders

g). Variational Autoencoders

h). Deep Belief Network

For more inputs on Tensor Flow you can connect here.
Contact the L&D Specialist at Locus IT.

Locus Academy has more than a decade experience in delivering the training/staffing on TensorFlow for corporates across the globe. The participants for the training/staffing on TensorFlow are extremely satisfied and are able to implement the learnings in their on going projects.


There are no reviews yet.

Be the first to review “Learn Deep Learning Applications Development with Tensor Flow”

Your email address will not be published. Required fields are marked *

TensorFlow allows developers to create dataflow graphs—structures that describe how data moves through a graph, or a series of processing nodes. Each node in the graph represents a mathematical operation, and each connection or edge between nodes is a multidimensional data array, or tensor.