top of page

GENERATIVE AI

(4.0) reviews

  • AI, ML, DL & Generative AI fundamentals

  • GANs, VAEs, Transformers, and Diffusion Models

  • Real-world projects: text generation, image synthesis, chatbots

  • Ethical AI and safety best practices

Syllabus

1

Introduction to AI and Generative Models

  1. Introduction to AI and Generative Models

  2. What is AI, ML, DL, and Generative AI

  3. Differences between discriminative vs generative models

  4. Real-world applications of Generative AI

2

Foundations of Machine Learning

  1. Supervised vs unsupervised learning

  2. Neural networks and deep learning basics

  3. Key concepts: overfitting, bias-variance, activation functions

3

Deep Learning for Generative AI

  1. Feedforward and convolutional neural networks (CNNs)

  2. Recurrent neural networks (RNNs), LSTMs, and GRUs

  3. Autoencoders and Variational Autoencoders (VAEs)

4

Generative Adversarial Networks (GANs)

  1. GAN architecture: Generator and Discriminator
    ​

  2. Training dynamics and challenges (mode collapse, convergence)

  3. GAN variants: DCGAN, CycleGAN, StyleGAN

7

Tools & Libraries

  1. TensorFlow, PyTorch

  2. Hugging Face Transformers

  3. OpenAI, Cohere, Stability AI APIs

5

Transformers and Large Language Models

  1. Transformer architecture: attention, encoder-decoder

  2. Pretraining and fine-tuning of language models

  3. Applications: text generation, summarization, chatbots

8

Ethical Considerations and Safety

  1. Bias in generative models

  2. Deepfakes and misinformation

  3. AI alignment and responsible use

6

Diffusion Models and Other Techniques

  1. Basics of diffusion models and their training

  2. Comparison with GANs and VAEs

  3. Use cases: image, video, and audio generation

9

Hands-on Projects

  1. Text generation with GPT

  2. Image synthesis with GANs or diffusion models

  3. Build your own chatbot or AI artist

bottom of page