DATAMARCOS

Generative AI

Generative AI For Beginners

Topic of the course

   - Definition and Overview of Generative AI

   - How Generative AI differs from traditional AI approaches

   - Key AI subfields involved (Deep Learning, Neural Networks)

   - Real-world applications of Generative AI (Text, Image, Music Generation)

   - Definitions and Key Differences

   - Role of Probabilistic Models

   - Use Cases of Generative Models (GANs, VAEs)

   - Use Cases of Discriminative Models (CNNs, SVMs)

   - Practical Scenarios: When to use Generative vs. Discriminative AI

   - Definitions and Key Differences

   - Role of Probabilistic Models

   - Use Cases of Generative Models (GANs, VAEs)

   - Use Cases of Discriminative Models (CNNs, SVMs)

   - Practical Scenarios: When to use Generative vs. Discriminative AI

   - Introduction to GANs: What they are and how they work

   - Components of GANs: Generator and Discriminator

   - Training Process and Loss Functions

   - Applications: Image Synthesis, Deepfakes, Data Augmentation

   - Common GAN Architectures: DCGAN, StyleGAN

   - Challenges with GANs: Mode Collapse, Training Instabilities

   - Hands-on Demo: Training a simple GAN

- Introduction to VAEs and How They Differ from GANs

   - Structure of a VAE: Encoder, Decoder, and Latent Space

   - Understanding Variational Inference

   - Applications of VAEs: Anomaly Detection, Image and Text Generation

   - Hands-on Example: Implementing a Basic VAE

- Introduction to Prompt Engineering - Crafting Effective Prompts for AI Models - Examples of Different Prompt Structures - Using Prompts to Guide AI Output (Creative Tasks, Coding, Language Translation) - Challenges in Prompt Engineering (Ambiguity, Misinterpretation) - Hands-on Exercise: Writing Prompts for Specific Tasks

   - Overview of OpenAI API: Capabilities and Use Cases

   - Moderation:

     - How the Moderation API Works

     - Using AI to Detect Harmful or Inappropriate Content

   - Chat Completion:

     - Building Conversational Agents

     - Best Practices for Using GPT for Conversations

   - Fine-tuning:

     - Process of Fine-tuning Pre-trained Models for Custom Tasks

     - Fine-tuning Techniques and Common Mistakes

     - Hands-on Demo: Fine-tuning GPT on a Custom Dataset

   - Function Calling:

     - What Function Calling is and Use Cases

     - Integrating Function Calling into Business Applications

     - Example: Using Function Calling to Retrieve Real-time Data

- What is LangChain? Overview and Key Features

   - Building AI Applications using LangChain

   - Understanding LLM (Large Language Models) Chains

   - Integrating External Tools with LangChain (Search Engines, Databases)

   - Hands-on Demo: Setting Up a Simple LangChain Project

   - Use Cases: Building Chatbots, AI-Assisted Tools

   - What is Vertex AI: Overview and Features

   - Vertex AI vs. Other AI Platforms (Azure ML, AWS Sagemaker)

   - Building and Deploying Models using Vertex AI

   - Managed Pipelines and Workflow Automation in Vertex AI

   - Integrating Vertex AI with Other Google Cloud Services

   - High-level Introduction to Vertex AI Co-pilot

   - Example Use Case: Deploying a Pre-trained Model with Vertex AI

   - Introduction to AI Ethics: Why It Matters

   - Ethical Concerns with Generative AI (Bias, Misinformation, Misuse)

   - Addressing Bias in Generative Models

   - Implementing Fairness and Transparency in AI Models

   - Regulatory Considerations: GDPR, AI-specific Laws

   - Real-world Examples of AI Misuse and Lessons Learned

- Use Cases of Generative AI in Various Industries:

     - Healthcare: Medical Image Generation

     - Marketing: Text and Ad Generation

     - Finance: Fraud Detection, Synthetic Data Generation

     - Entertainment: Content Creation (Movies, Games)

   - Hands-on Exercise: Exploring a Use Case and Developing an AI Solution

- Objective: Craft Effective Prompts for Language Models

   - Steps:

     - Introduction to Task

     - Writing Prompts for Specific Outputs (e.g., Product Descriptions, Text Summarization)

     - Evaluating Output: Correctness, Coherence, Creativity

     - Adjusting Prompts to Improve Results

   - Insights and Conclusion: Learning to Fine-tune Prompts for Better AI Results

Scroll to Top