Deep Learning Foundations for AI and Gen AI

Name: Deep Learning Foundations for AI and Gen AI
Rating: 4.4 (392 reviews)

How deep learning works? Why is it a foundation to Gen AI? How do you handle sequence modeling?

Created byDr Sunil Kumar Vuppala

Last updated 3/2026

English

English [Auto],

What you'll learn

To provide a comprehensive understanding of the deep learning concepts and applications both in traditional AI and Gen AI
Master the Core Mechanics of a Neural Network, including the functions of the forward pass and the backpropagation learning mechanism
Implement and Interpret Deep Learning Models using practical tools (TensorFlow Playground) to understand parameters and the network learning process.
Analyze and Apply Sequence Modeling Architectures, the need for and the internal workings of RNNs and LSTMs to handle long, sequential data
Part-2 cover the attention models, transformer models and GPT

Course content

6 sections • 27 lectures • 2h 57m total length

Overview1:07
This introduction video is about what you will learn in the course of deep learning foundations for AI and Gen AI.
Contents of module-11:38
Contents of the module 1 are discussed in this video

Applications and data types8:21
Explore how deep learning uses diverse data types—numerical, categorical, text, image, video, speech, and signals—converting them into vectors for CNN and RNN backbones.
Learning Journey of deep learning till Generative AI3:08
Trace the learning journey from deep learning foundations through feedforward and recurrent networks to lstm, sequence-to-sequence models, and transformers, including BERT, GPT, and llms, with a focus on frugal AI.
AI stages7:14
AI, ML, DL, and GenAI Hierarchy

History of Deep Learning3:54
Imagenet Challenge7:30
Second Wave4:35
Machine Learning vs Deep Learning5:53
Differentiate machine learning from deep learning: deep learning learns features automatically, while machine learning uses explicit feature extraction. Use cases include anomaly detection, regression, and classification with transfer learning.
Learning mechanisms6:27
Brain working7:22
Artificial Neural Networks4:31
Leaning Mechanism and History of Deep Learning
Learning mechanisms and Deep learning history

Intro to Tensorflow playground12:27
Explore how the TensorFlow playground visualizes neural networks and distinguishes parameters from hyperparameters, and explain epochs, iterations, batch size, learning rate, activation functions, and regularization (L1 and L2).
Learning in Tensorflow playground9:54
Explore how neural networks in TensorFlow playground move from simple linear separation to complex boundaries, by tuning hyperparameters, regularization, and feature transformations for better generalization.
Complex cases in Tensorflow Playground3:59
Parameters in Deep Learning: Tensorflow playground1:08
Deep Learning Parameters

Recurrent Neural Networks Introduction0:48
Explore sequence modeling with recurrent neural networks, learn why feedforward nets struggle with sequences, examine RNNs' challenges, and uncover LSTM solutions and real-world applications.
Sequence Modeling5:19
Language modeling and need for RNN6:20
Recurrent Neural Networks (RNN) concept and network8:49
Challenges in RNN5:08
Long Short Term Memory (LSTM)12:55
Explore the LSTM long short term memory, detailing its three gates: forget, input, and output, and how the cell state combines long-term and short-term memory to manage information flow.
Summary of LSTM and Next Steps2:46
Practice test on Back propagation and recurrent neural networks
Testing the RNN and LSTM knowledge

Requirements

Mathematics, Programming, and Foundational Machine Learning Concepts

Description

This course provides a robust curriculum on the foundational principles of Deep Learning (DL) and its essential role in the Generative AI (Gen AI) landscape. The learning journey starts by defining the path towards Gen AI, clearly answering key questions such as "What is Deep learning?" and "Why is it a foundation to Gen AI?" A core segment of the course focuses on the theoretical and practical difference between Machine Learning and Deep Learning.

A significant portion is dedicated to the mechanics of a neural network, detailing the processes of the forward pass and the crucial learning algorithm: backpropagation. Leaners will gain an in-depth understanding of parameters and the learning mechanism through practical understanding with the TensorFlow playground and a network simulator.

The curriculum then advances to critical applications, specifically sequence modeling. It explores the challenges of handling sequential data, justifying the need for specialized architectures like Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM). The course thoroughly explains the internal workings of RNN and LSTM, focusing on why these models require memory to effectively manage and process long sequences, providing students with a complete skill set in both foundational DL and advanced sequence processing. This is part-1 in the series. Next part will focus on Attention models, transformers and GPT.

Who this course is for:

Students, Working professionals, Recent Graduates, Faculty members

Deep Learning Foundations for AI and Gen AI

What you'll learn

Explore related topics

Course content

Introduction2 lectures • 3min

Applications, Leaning Journey and AI stages3 lectures • 19min

Deep Learning history, Learning mechanisms and ANN7 lectures • 40min

Tensorflow playground4 lectures • 27min

Forward pass and Back propagation in Deep Learning4 lectures • 46min

Recurrent Neural Networks and LSTM7 lectures • 42min

Requirements

Description

Who this course is for: