Generative AI Full Course – Gemini Pro, OpenAI, Llama, Langchain, Pinecone, Vector Databases & More

Generative AI Full Course – Gemini Pro, OpenAI, Llama, Langchain, Pinecone, Vector Databases & More

Created by

Jittesh Purrohit

326:00:00 Hours

0 Enrolled

    • (0 Reviews)

English

Last updated

Fri, 18-Oct-2024

Course description

Course Overview:

This course provides an in-depth understanding of generative AI, covering the theoretical foundations, various models, and practical applications across different domains. Participants will engage in hands-on projects to apply their learning.

Course Duration:

  • Total Duration: 8 weeks
  • Sessions: 2 sessions per week
  • Session Length: 2 hours each

What will i learn?

  • Knowledge-Based Outcomes : Understanding of Generative AI Concepts: Explain the fundamental principles of generative AI and differentiate between generative and discriminative models. Describe various types of generative models, including VAEs, GANs, and Transformer-based models.
  • Skill-Based Outcomes Practical Implementation: Implement basic generative models (e.g., GANs, VAEs) using popular frameworks like TensorFlow or PyTorch. Conduct data preprocessing, model training, and evaluation of generative models.
  • Hands-On Project Development: Design and develop a project that applies generative AI techniques to a real-world problem (e.g., image generation, text synthesis). Present and demonstrate the outcomes of the project to peers, showcasing both technical skills and creative applications.
  • Real-World Application: Apply generative AI techniques to various domains, such as art, music, healthcare, and natural language processing. Explore and implement advanced applications of generative AI, such as deepfakes, style transfer, or automated content generation.

Requirements

  • Requirements for Generative AI Course : Technical Setup: A laptop or desktop computer with internet access. Installation of relevant software and libraries (e.g., Python, TensorFlow, PyTorch, Jupyter Notebook). Course Materials: Access to recommended textbooks, articles, and online resources. Familiarity with a coding environment (e.g., Jupyter Notebook, Google Colab).
  • Prerequisites for Participants Basic Programming Skills: Proficiency in Python, as it is the primary language used in most AI frameworks and libraries. Understanding of data structures (lists, dictionaries, etc.) and control structures (loops, conditionals).
  • Mathematics and Statistics: Fundamental knowledge of linear algebra (vectors, matrices, matrix operations). Basic calculus concepts, particularly derivatives and gradients. Understanding of probability and statistics (distributions, mean, variance).
  • Fundamentals of Machine Learning: Familiarity with basic machine learning concepts, including supervised and unsupervised learning. Understanding of common algorithms (e.g., linear regression, decision trees). Knowledge of overfitting, underfitting, and model evaluation metrics.

Frequently asked question

Generative AI is a type of machine learning (ML) model that can take what it has learned from the examples it has been provided to create new content, such as text, images, music, and code. These models learn through observation and pattern matching, also known as training. For example, a model may learn what a cat looks like by observing many different examples of cats and recognizing characteristics consistent with a cat. The same goes for sonnets, resumes, or packing lists for a camping trip.

Large Language Models, or LLMs, are generative AI models which can predict words that are likely to come next, based on the user’s prompt and the text it has generated so far. In some cases, LLMs can respond to the same prompt with different responses. This is due to the flexibility that LLMs are often given to pick among probable words that could follow, based on patterns identified from their training data. This flexibility allows them to generate more interesting and creative responses.

Much of the recent progress we’ve seen in AI is based on machine learning (ML), a subfield of computer science where computers learn to mathematically recognize patterns from example data, rather than being programmed with specific rules. Deep learning is a specific ML technique based on neural networks. Neural networks use nodes or “artificial neurons,” inspired by models of brain neurons, as fundamental processing units which receive and pass numeric inputs and outputs from other neurons. Deep learning connects multiple layers of these artificial neurons

  • Chapter 01 08:00:00
    Introduction to Generative AI
    Summary:

    Introduction to Generative AI

  • Chapter 01 54:00:00
    Lesson 1 : Structure of Neural Networks
    Summary:

    Lesson 1 : Structure of Neural Networks

  • Chapter 02 13:00:00
    Lesson 3: Training Neural Networks
    Summary:

    Lesson 3: Training Neural Networks

  • Chapter 01 05:00:00
    Lesson 4 : Introduction to Generative AI Models
    Summary:

    Introduction to Generative AI - LLM

  • Chapter 02 18:00:00
    Lesson 5 : Variational Autoencoders (VAEs)
    Summary:
  • Structure and training of VAEs
  • Applications of VAEs in data generation and representation learning

  • Chapter 01 14:00:00
    Lesson 6 : Understanding GANs
    Summary:
  • Architecture of GANs (generator and discriminator)
  • The adversarial training process
  • Chapter 02 40:00:00
    Session 7 : Advanced GAN Variants
    Summary:
    Advanced GAN Variants & its implementation on Python

    • Chapter 01 90:00:00
      Lesson 8 : Introduction to Transformers
      Summary:
      Introduction to Transformers
      The transformer architecture and attention mechanism
      Comparison with traditional RNNs and LSTMs
    • Chapter 02 54:00:00
      Lesson 9 : Generative Pre-trained Transformers (GPT)
      Summary:
      Generative Pre-trained Transformers (GPT)
      Overview of GPT models (GPT-2, GPT-3, etc.)
      Applications in text generation and natural language understanding

    • Chapter 01 30:00:00
      Lesson 10 : Practical Applications for Gen AI
      Summary:
      Module 6: Practical Applications of Generative AI
      Session 11: Text Generation Applications
      Building chatbots and conversational agents
      Text summarization and story generation

    • Chapter 01
      Generative AI - Project Development
      Summary:
      Module 8: Hands-On Projects and Future Directions (Week 8)
      Session 10 : Project Development
      Choosing a project topic (text, image, or audio generation)
      Data collection and preprocessing techniques
      Session 11: Project Presentations and Future Trends
      Presenting projects to peers
      Discussing future trends and potential research areas in generative AI

    Jittesh Purrohit

    View profile

    Lectures

    11

    Skill level

    Advanced

    Expiry period

    Lifetime
    Enquire now

    Related courses

    Study any topic, anytime. explore thousands of courses for the lowest price ever!

    Top categories

    Useful links

    Help

    Subscribe to our newsletter