AI Fundamentals Training Overview
This Fundamentals of Artificial Intelligence/Deep Learning/Generative AI Models training course teaches attendees how to use the Python programming language to build modern machine learning (ML) applications that incorporate the latest ML technologies such as generative AI, deep learning, natural language processing, and computer vision.
Learners are introduced to the basic concepts of Python, such as variables, data types, functions, and control flow. They also learn how to use the Anaconda computing environment, which comes with many valuable tools for data science.
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
- Understand the basics of machine learning
- Prepare data for machine learning
- Build and evaluate machine learning models
- Apply machine learning to real-world problems
- Explore the latest trends in machine learning
- Review core Python concepts
- Use the Anaconda computing environment
- Import and manipulate data with Pandas
- Perform exploratory data analysis with Pandas and Seaborn
- Understand Artificial Neural Networks (ANNs) and deep learning
Prerequisites
All attendees must have prior experience using Python to perform exploratory data analysis and develop predictive models using machine learning techniques. Students must also have familiarity with base Python coding.
Outline
Expand All | Collapse All
Introduction
Review of Core Python Concepts (**if needed – depends on tool context**)
- 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
Hands-on 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 Convergence of a Neural Network
- Hyperparameter tuning
- Evaluating Models
- Scoring New Datasets with a Model
Using Deep Learning for Prediction Models
Hands-on Deep Learning Model Construction for Prediction Models
- Preprocessing Tabular Datasets for Deep Learning Workflows
- Data Validation Strategies
- Architecture Modifications to Managing Over-fitting
- Regularization Strategies
- Deep Learning Classification Model example
- Deep Learning Regression Model example
Extending Deep Learning Models to more complex (heterogenous) data inputs
- What happens if we do not have a rectangle of data as the input?
- Pre-processing sequence data (i.e., time series) to use as inputs to feed-forward ANN
- Exploring model architectures that can handle sequence data
- Recurrent Neural Network (RNN)
- Long Short Term Memory (LSTM)
- Transformers
- Extending model architecture to handle heterogenous (Sequence and non-sequence) data
Natural Language Processing with Deep Learning
- Common use cases for text data and deep learning
- Exploratory Data Analysis on text data
- Cleaning/pre-processing text data
- Understanding word embeddings
- Text Classification models
- Bag of Words approach
- RNN / LSTM modeling approaches
- Transfer learning with text classification models: using BERT
- Using Hugging Face to start with state-of-the-science models
- Fine-tuning the model on your datasets
Computer Vision with Deep Learning
- Common AI use cases with images
- Exploratory Data Analysis on image data
- Pre-processing images
- Data augmentation with existing images
- Image classification examples
- Image classification with ANN
- Image classification with convolutional neural networks
- Image classification and transfer learning:
- Using Hugging Face to start with state-of-the-science models
- Fine-tuning the model on your datasets
- Image segmentation and transfer learning
- Using Hugging Face to start with state-of-the-science models
- Fine-tuning the model on your datasets
Generative AI with Deep Learning
- Generative AI fundamentals
- Generating new content versus analyzing existing content
- Example use cases: text, music, artwork, code generation
- Ethics of generative AI
- Sequence Generation with RNN
- Recurrent neural networks 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
- Overview of current popular large language models (LLM)
- Medium-sized LLM in your environment
- Stanford Alpaca
- Facebook Llama
- Transfer learning with your data in these contexts
Conclusion
Training Materials
All AI Fundamentals training students receive comprehensive courseware.
Software Requirements
- A modern web browser and an Internet connection
- Windows, Mac, or Linux
- A current version of Anaconda for Python 3.x, or a comparable Python installation with the necessary libraries (Accelebrate can provide a list)
