Share Description
In this course, you will :
- All of the tools you need to become an AI engineer are included in the course.
- Build a strong foundation by comprehending the fundamental ideas of artificial intelligence.
- Learn how to utilize Python for NLP and AI by beginning to code in the language.
- Demonstrate your knowledge of the AI field to interviewers.
- Utilize your abilities in practical business situations.
- Make use of large language models' power.
- Chain interoperable components together with LangChain to create AI-driven applications with ease.
- Learn about Hugging Face and its AI capabilities.
- Connect to strong foundation models by using APIs.
- For more sophisticated speech-to-text, use Transformers.
Syllabus:
- Intro to AI Module: Getting started
- Intro to AI Module: Data is essential for building AI
- Intro to AI Module: Key AI techniques
- Intro to AI Module: Important AI branches
- Intro to AI Module: Understanding Generative AI
- Intro to AI Module: Practical challenges in Generative AI
- Intro to AI Module: The AI tech stack
- Intro to AI Module: AI job positions
- Intro to AI Module: Looking ahead
- Python Module: Why Python?
- Python Module: Setting Up the Environment
- Python Module: Python Variables and Data Types
- Python Module: Basic Python Syntax
- Python Module: More on Operators
- Python Module: Conditional Statements
- Python Module: Functions
- Python Module: Sequences
- Python Module: Iteration
- Python Module: A Few Important Python Concepts and Terms
- NLP Module: Introduction
- NLP Module: Text Preprocessing
- NLP Module: Identifying Parts of Speech and Named Entities
- NLP Module: Sentiment Analysis
- NLP Module: Vectorizing Text
- NLP Module: Topic Modelling
- NLP Module: Building Your Own Text Classifier
- NLP Module: Categorizing Fake News (Case Study)
- NLP Module: The Future of NLP
- LLMs Module: Introduction to Large Language Models
- LLMs Module: The Transformer Architecture
- LLMs Module: Getting Started With GPT Models
- LLMs Module: Hugging Face Transformers
- LLMs Module: Question and Answer Models With BERT
- LLMs Module: Text Classification With XLNet
- LangChain Module: Introduction
- LangChain Module: Tokens, Models, and Prices
- LangChain Module: Setting Up the Environment
- LangChain Module: The OpenAI API
- LangChain Module: Model Inputs
- LangChain Module: Message History and Chatbot Memory
- LangChain Module: Output Parsers
- LangChain Module: LangChain Expression Language (LCEL)
- LangChain Module: Retrieval Augmented Generation (RAG)
- LangChain Module: Tools and Agents
- Vector Databases Module: Introduction
- Vector Databases Module: Basics of Vector Space and High-Dimensional Data
- Vector Databases Module: Introduction to The Pinecone Vector Database
- Vector Databases Module: Semantic Search with Pinecone and Custom (Case Study)
- Speech Recognition Module: Introduction
- Speech Recognition Module: Sound and Speech Basics
- Speech Recognition Module: Analog to Digital Conversion
- Speech Recognition Module: Audio Feature Extraction for AI Applications
- Speech Recognition Module: Technology Mechanics
- Speech Recognition Module: Setting Up the Environment
- Speech Recognition Module: Transcribing Audio with Google Web Speech API
- Speech Recognition Module: Background Noise and Spectrograms
- Speech Recognition Module: Transcribing Audio with OpenAI's Whisper
- Speech Recognition Module: Final Discussion and Future Directions
- LLM Engineering Module: Introduction
- LLM Engineering Module: Planning stage
- LLM Engineering Module: Crafting and Testing AI Prompts
- LLM Engineering Module: Getting to Know Streamlit
- LLM Engineering Module: Developing the prototype
