Generative AI Training Overview
This Fundamentals of Deep Learning and Generative AI Models course teaches attendees the fundamentals of Machine Learning (ML) and deep learning using Python programming. Participants learn how to use Python to import and manipulate data, perform exploratory data analysis, and build machine learning models. Attendees also learn about the different types of ML models, classification and regression, and Neural Networks.
Location and Pricing
Accelebrate offers instructor-led enterprise training for groups of 3 or more online or at your site. Most Accelebrate classes can be flexibly scheduled for your group, including delivery in half-day segments across a week or set of weeks. To receive a customized proposal and price quote for private corporate training on-site or online, please contact us.
In addition, some courses are available as live, instructor-led training from one of our partners.
Objectives
- Construct predictive models using machine learning and deep learning techniques, understanding their applications and limitations
- Build and evaluate artificial neural networks (ANNs) for various tasks, optimizing their architecture and monitoring convergence
- Develop robust deep learning models for classification and regression tasks, implementing preprocessing, validation, and regularization strategies
- Apply generative AI techniques to create new content across various domains, understanding the ethical considerations involved
- Utilize recurrent neural networks (RNNs) and variational autoencoders (VAEs) for sequential data generation and other applications
- Create generative adversarial networks (GANs) to generate realistic data samples and address adversarial examples
- Leverage transformer architectures for natural language processing and time series classification tasks
- Explore popular large language models (LLMs) like ChatGPT, DALL-E 2, and Bing AI, and understand their capabilities
- Fine-tune medium-sized LLMs like Stanford Alpaca and Facebook Llama with your own data for specific use cases
Prerequisites
All attendees must have experience developing Deep Learning models, including architectures such as feed-forward artificial Neural Networks, recurrent, and convolutional.
Outline
Expand All | Collapse All
Review of Core Python Concepts (optional)
- Anaconda computing environment
- Importing and manipulating data with Pandas
- Exploratory data analysis with Pandas and Seaborn
- NumPy ndarrays versus Pandas dataframes
Overview of Machine Learning/Deep Learning
- Developing predictive models with ML
- How Deep Learning techniques have extended ML
- Use cases and models for ML and Deep Learning
Introduction to Artificial Neural Networks (ANNs) and Deep Learning
- Components of Neural Network Architecture
- Evaluate Neural Network fit on a known function
- Define and monitor the convergence of a Neural Network
- Evaluating models
- Scoring new datasets with a model
Deep Learning Model Construction for Prediction
- Preprocessing tabular datasets for Deep Learning workflows
- Data validation strategies
- Architecture modifications for managing over-fitting
- Regularization strategies
- Deep Learning classification model example
- Deep Learning regression model example
- Trustworthy AI Frameworks for this DL prediction context
Generative AI Fundamentals
- Generating new content versus analyzing existing content
- Example use cases: text, music, artwork, code generation
- Ethics of Generative AI
Sequential Generation with Recurrent Neural Networks (RNN)
- RNN overview
- Preparing text data
- Setting up training samples and outputs
- Model training with batching
- Generating text from a trained model
- Pros and cons of sequential generation
Variational Autoencoders
- What is an autoencoder?
- Building a simple autoencoder from a fully connected layer
- Sparse autoencoders
- Deep convolutional autoencoders
- Applications of autoencoders to image denoising
- Sequential autoencoders
- Variational autoencoders
Generative Adversarial Networks
- Model stacking
- Adversarial examples
- Generational and discriminative networks
- Building a generative adversarial network
Transformer Architectures
- The problems with recurrent architectures
- Attention-based architectures
- Positional encoding
- The Transformer: attention is all you need
- Time series classification using transformers
Overview of Current Popular Large Language Models (LLM)
Medium-sized LLM in Your Own Environment
- Stanford Alpaca
- Facebook Llama
- Transfer learning with your own data in these contexts
Conclusion
Training Materials
All Deep Learning training students receive comprehensive courseware.
Software Requirements
All attendees must have a modern web browser and an Internet connection.
