Course
AI For Data Science
45 hours 53 minutes
Credits: 3 Credits
Description
This course teaches software engineers how to understand and apply generative AI, deep learning, and natural language processing (NLP) using modern tools and frameworks. Starting from foundational AI and generative modeling concepts, learners progress through transformer architectures, recurrent networks, and LLMs, before advancing to hands-on NLP development using Hugging Face, fine-tuning models, and building Retrieval-Augmented Generation (RAG) applications.
What Students Will Learn
Chapter 1: Activate
- AI Landscape Literacy (Beginner Level)
- An Introduction to Generative AI Concepts
- Generative Modeling Foundations
- Getting Started with Large Language Models (LLMs)
- Exploring the Depths of Large Language Models in Generative AI
- Leveraging Generative AI for Business
- Artificial Intelligence and Machine Learning
- Deep Learning and Neural Networks
- An Introduction to GPT Models
- Considerations for Using AI Responsibly
Chapter 2: Accelerate
- NLP with Deep Learning Competency (Intermediate Level)
- Generative AI Models: Getting Started with Autoencoders
- Generative AI Models: Generating Data Using Variational Autoencoders
- Generative AI Models: Generating Data Using Generative Adversarial Networks
- Natural Language Processing Using Deep Learning
- Using Recurrent Networks For Natural Language Processing
- Using Out-of-the-Box Transformer Models for Natural Language Processing
- Attention-based Models and Transformers for Natural Language Processing
- Transformers: The "T" in GPT
- Exploring Transformers with Hugging Face
- Exploring Transformers Lab: Exploring Their Carbon Footprint
Chapter 3: Transform
- NLP and LLMs Competency (Intermediate Level)
- NLP with LLMs: Working with Tokenizers in Hugging Face
- NLP with LLMs: Hugging Face Classification, QnA, & Text Generation Pipelines
- NLP with LLMs: Language Translation, Summarization, & Semantic Similarity
- NLP with LLMs: Fine-tuning Models for Classification & Question Answering
- NLP with LLMs: Fine-tuning Models for Language Translation & Summarization
- Introduction to Finetuning
- Finetuning Transformers with Hugging Face
- Finetuning Language Models: Practice Lab
- RAG Foundations
- Build a RAG App
- RAG Techniques
Optional
- Learn Data Science from Scratch: Mastering ML and NLP with Python in a step-by-step approach
Overall Learning Outcomes
- Explain generative AI concepts, generative modeling foundations, and large language model architectures including GPT models
- Apply AI and machine learning principles including deep learning, neural networks, and responsible AI usage
- Leverage generative AI for business use cases and practical applications
- Build and work with autoencoders, variational autoencoders, and generative adversarial networks (GANs)
- Implement NLP solutions using deep learning, recurrent networks, transformers, and attention-based models
- Use Hugging Face transformers for text generation, sentiment analysis, classification, and summarization
- Fine-tune LLMs for classification, question answering, language translation, and summarization using PEFT techniques
- Build tokenizer pipelines and NLP workflows using Hugging Face libraries
- Design and implement RAG applications using foundational and advanced retrieval-augmented generation techniques
- Demonstrate intermediate-level competency in NLP with deep learning and NLP with LLMs through skill benchmarks