Deep Learning is one of the key areas of AI. This course is one of the constituent courses of our course “AI Engineer”, offered jointly by Simplilearn and IBM.

This comprehensive course provides knowledge and skills to deploy deep learning tools using AI / Machine Learning frameworks effectively. Learners will explore fundamental concepts & practical applications of Deep Learning, while gaining clear understanding of distinctions between Deep Learning and Machine Learning.

The course covers wide range of topics, including Neural Networks, forward and backward propagation, TensorFlow 2, Keras, performance optimization techniques, model interpretability, Convolutional Neural Networks (CNNs), transfer learning, object detection, Recurrent Neural Networks (RNNs), autoencoders, & creating neural networks in PyTorch.

By the end of the course, you will have solid foundation in Deep Learning principles and ability to build and optimize Deep Learning models effectively using Keras and TensorFlow.

• Differentiate between Deep Learning and Machine Learning and understand their respective applications
• Gain comprehensive understanding of different types of neural networks
• Master concepts of forward propagation and backward propagation in deep neural networks (DNN)
• Obtain introduction to modeling and learn techniques for improving performance in Deep Learning models
• Comprehend hyperparameter tuning & model interpretability
• Learn about dropout and early stopping techniques and their implementation
• Gain expertise in convolutional neural networks (CNN)and object detection
• Grasp fundamentals of recurrent neural networks (RNN)
• Understand basics of PyTorch& learn how to create neural network using PyTorch

Lesson 01: Course Introduction

Lesson 02: Introduction to Deep Learning

Lesson 03: Perceptron

Lesson 04: Deep Neural Networks(DNN)

Lesson 05: TensorFlow2

Lesson 06: Model Optimization and Performance Improvement

Lesson 07: Convolutional Neural Networks (CNN)

Lesson 08: Transfer Learning

Lesson 09: Object Detection

Lesson 10: Recurrent Neural Networks (RNN)

Lesson 11: Transformer Models for NLP

Lesson 12: Getting Started with Autoencoders

Lesson 13: PyTorch

English

1. Different batches of Live Virtual Classes (LVCs) available, & learners can choose the batch convenient to them
2. If learner misses a session of LVC, by watching 50% or more of the recording subsequent to the class, it is also deemed as “Present”.
3. One year access to Learning Management System (LMS) from the date of activation of LMS.
4. Recordings of registered LVCs available post-class, during access period to LMS
5. Subject to T & Cs , as updated from time to time

customer@the-pti.com

customer@the-pti.com