Duration: Hours

Keras is the high-level API of TensorFlow 2: an approachable, highly-productive interface for solving ML problems, with a focus on modern deep learning. It is written in Python and is used to make the implementation of neural networks easy.

Training Mode: Online


Objective :

1. Use the powerfully functional Keras API to design and implement advanced deep learning techniques
2. Design and implement advanced Convolutional Neural Networks for powerful image classification
3. Design and implement object detection networks to identify objects present in images and their location
4. Work with deep generative neural networks for synthetic data generation and semi-supervised learning
5. Develop a stable deep reinforcement-learning system and learn to make optimal decisions via feedback from their environment.


a). Familiarity with machine learning approaches and practical experience with Keras are assumed. Fluency with Python programming is assumed.

1. Preparing yourself for Mastering Keras Journey

a). Keras and TensorFlow Functionalit

b). Setting Up the Environment and Teaching Methodology

2. Working with the Keras API Functionality

a). MLPs and Simple Data Analytics

b). CNNs and Basic Image Classification

c). RNNs and Sequential Data Analysis

d). AEs and Denoising Data

3. Developing and Implementing Deep Generative Models

a). What can generative model do for me

b). Implementing GANs in Keras

c). Implementing VAEs in Keras

4. Advanced CNNs

a). Working with Inception Networks/Layers

b). Residual Networks/Layers

c). Dense Networks

d). Transfer Learning: Applying Advanced Architectures on Real Data

5. Object Detection

a). Introduction to Object Detection Networks

b). Fast RCNNs

c). Region Proposal Networks and Faster RCNNs

6. Deep Reinforcement learning

a). Reinforcement Learning Basics

b). (Epsilon) Q-Learning and Deep Q-Networks

c). Dealing with Instability (1): Experiential Replay

d). Dealing with Instability (2): Double Deep Q-Networks

e). Advantage Networks

f). Actor-Critic Networks

g). Asynchronous Agents and A3C Networks

h). Implementing a Deep Reinforcement Learning

i). Discussion of Real-World Applications

7. One-Shot and Deep Semi-Supervised Learning

a). Significance of One-Shot Learning Methods

b). Siamese Networks

c). Semi-Supervised Learning

d). Semi-Supervised Learning Using Ladder Networks

e). Semi-Supervised Learning Using GANs


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


There are no reviews yet.

Be the first to review “Mastering Keras”

Your email address will not be published.