Loss function of a GAN | Pantech University

Autoplay
Autocomplete

Previous Lesson Complete and Continue

Internship on Generative AI

Mandatory Step First Step - Join the Community Here

Join Private Community
Join VIP Telegram Group

Note

Recordings will be updated on the upcoming days - one by one

Course Repository

Download Now

Introduction to AI, ML, and DL

Introduction to Artificial Intelligence (5:52)
Basic of ML & DL Projects (3:13)
Step Involved in a My DL Projects (6:45)
Different between Traditional AI vs Generative AI (4:33)
Supervised vs Unsupervised (11:51)
Hands-on 1 (24:01)
Generative AI DEMO (1:46)
Deeplearning (26:32)
GENERATIVE AI (3:30)
Basic math related to Linear Regression (1:49)
Program Mindset Session (7:20)

Python for Machine Learning

AGENDA (1:31)
Introduction to Numby Library (14:38)
Introduction to Pandas Library (13:58)
Introduction to Matplotlib Library (10:27)
Introduction to Scikit-Learn Library (1:47)
Hands-on Projects (26:11)

Day 3: Linear Algebra and Calculus for ML

Introduction (1:29)
Basics of Linear Algebra (11:02)
Performing mathematical operations using NumPy (7:01)
Gradient Descent Optimization (8:48)
Implementing Gradient Descent using Python (5:44)
Hands-on (12:26)

Day 4: Supervised and Unsupervised Learning

Supervised Learning (10:25)
Types of Supervised Learning Regression and Classification (4:09)
Unsupervised Learning (8:18)
Types of Unsupervised Learning - Clustering & Dimensionality Reduction (2:31)
K-Means Clustering (6:56)
Revising K-Means Clustering (3:15)
Hands-on Project (12:19)

Day 5: Model Evaluation and Cross-Validation

Introduction to Model Evaluation (2:17)
Evaluation Metrics (17:03)
Implementing Evaluation Metrics using NumPy (3:28)
Introduction to Cross-validation (3:41)
K-Fold Cross-validation concept (5:25)
Basic Cross-Validation Implementation (7:04)
Hands-on Project (18:53)

Day 6: Introduction to Neural Networks

Introduction (2:56)
What is a Neural Network (4:18)
Perceptrons (9:28)
Activation Function (9:17)
Backpropagation (8:15)
Hands-on (18:14)

Day 7: Convolutional Neural Networks (CNNs)

Revisiting Neural Networks (8:44)
Introduction to CNNs (2:23)
Architecture of CNNs (19:50)
Simple Convolution operation (4:47)
Implementing Max pooling (2:03)
Hands-on (21:16)

Day 8: Recurrent Neural Networks (RNNs)

Understanding RNNs (10:48)
Implementing a Simple RNN (16:21)
Hands-on (29:23)

Day 9: LSTM and GRU Networks

Introduction (2:55)
Need for LSTMs and GRUs (10:34)
Long Short Term Memory (LSTM) (8:09)
Gated Recurrent Units (GRU) (8:33)
Hands-on (19:46)

Day 10: Autoencoders and Variational Autoencoders (VAEs)

Agenda for the session (1:00)
What is an Autoencoder? (3:52)
Working of Autoencoders (1:51)
Architecture of Autoencoders (5:00)
Variational Autoencoders (VAEs) (11:27)
Hands-on (30:12)

Day 11: Introduction to GANs

Introduction to GANs (12:04)
GAN Architecture (9:05)
Working of GAN (6:00)
Loss function of a GAN (4:36)
Hands-on (33:12)

Day 12: Deep Convolutional GAN (DCGAN)

Agenda for the session (3:58)
Introduction to DCGAN (3:06)
Architecture of DCGAN (5:16)
Hands-on (40:16)

Day 13: Wasserstein GAN (WGAN)

Agenda for the session (1:50)
Intro to WGAN (6:53)
Loss Function of a WGAN (3:14)
The WGAN Algorithm (4:46)
Hands-on (22:08)

Day 14 - Conditional GANs (cGANs)

Agenda for the session (0:57)
Introduction to Conditional GANs (3:53)
Applications and examples of CGANs (4:49)
Architecture of a CGAN (4:44)
Summary of CGAN (1:00)
Answering few doubts (3:38)
Hands-on Implementation (29:01)

Day 15 - CycleGAN

Agenda for the session (1:49)
Introduction to CycleGANs (3:21)
Applications of CycleGANs (2:54)
Working of CycleGAN (5:23)
Architecture of a CycleGAN (3:27)
Steps Involved (10:12)
Hands-on (28:01)

Event Recordings

Day 16 - Introduction to Language Models (60:44)
Day 17 - Transformer Architecture (66:44)
Day 18 - Hugging Face and Pre-trained Models (27:43)
Day 19 - Text Summarization and Question Answering (58:25)
Day 20 - Machine Translation (31:25)
Day 21- Introduction to Retrieval-Augmented Generation (RAG) (62:39)
Day 22 -LangChain for LLMs (45:20)
Day 23 - Few-shot and Zero-shot Learning (26:21)
Day 24 - Prompt Engineering (39:03)
Day 25 - Advanced Fine Tuning Techinques (38:53)
Day 26 - Generative Models for Healthcare Applications (42:19)
Day 27 - Generative Models for Scientific Applications (70:27)
Day 28 - Generative Models for Art and Design (58:14)
Day 29 - Generative Models for Audio and Time Series (49:22)
Day 30 - Real-world - Final Project (27:42)

Teach online with

Loss function of a GAN

Lesson content locked

If you're already enrolled, you'll need to login.

Enroll in Course to Unlock