Wolfram Microcredentials

AI Programming with Wolfram Language

1
.
Wolfram Notebook and Language Basics

AI Assistance in Wolfram Notebooks

◼
  • Accessing Notebook Assistant
    • ◼
  • Asking for Code and Improving Code
    • ◼
  • Computing with Images and Real-World Data
    • ◼
  • Publishing a Web Form
    • ◼
  • Working with Chat Cells
    • ◼
  • Quiz 1

    • Working with Wolfram Notebooks

    ◼
  • Adding Content to a Notebook
    • ◼
  • Cells in a Notebook
    • ◼
  • Writing and Evaluating Code
    • ◼
  • Useful Things to Know
    • ◼
  • Using Natural Language for Computation
    • ◼
  • LLM-Based Input Options
    • ◼
  • Quiz 2

    • Getting Started with Wolfram Language

    ◼
  • Try a Few Things
    • ◼
  • Lists
    • ◼
  • Structure of Expressions
    • ◼
  • Repeated Evaluation
    • ◼
  • Manipulate
    • ◼
  • Immediate and Delayed Assignment
    • ◼
  • Defining a Function
    • ◼
  • Pure Functions
    • ◼
  • Tips and Tricks
    • ◼
  • Quiz 3
    • 2
    .
    Machine Learning Superfunctions

    Supervised Learning Functions

    ◼
  • Classify
    • ◼
  • Classification Exercise
    • ◼
  • A Workflow for Classification
    • ◼
  • Predict
    • ◼
  • Predicting Sequential Data
    • ◼
  • Training Methods
    • ◼
  • Options for Classify and Predict
    • ◼
  • Working around Common Issues
    • ◼
  • Quiz 1

    • Unsupervised Learning Functions

    ◼
  • Feature Extraction
    • ◼
  • Feature Space Distance and Clustering
    • ◼
  • Anomaly Detection, LearnDistribution and Missing Values
    • ◼
  • Quiz 2
    • 3
    .
    Wolfram Neural Net Framework

    Neural Net Overview

    ◼
  • Neural Nets through the Years
    • ◼
  • Image Processing
    • ◼
  • Audio and Video Processing
    • ◼
  • Text Processing
    • ◼
  • What Is a Neural Net Exactly?
    • ◼
  • As Explained by a Neural Net Pioneer
    • ◼
  • Building Blocks of Neural Nets, Part 1
    • ◼
  • Building Blocks of Neural Nets, Part 2
    • ◼
  • Wolfram Neural Net Repository
    • ◼
  • Building a Simple Network
    • ◼
  • Building a More Complex Network
    • ◼
  • Training Your Own Network
    • ◼
  • Training a Pre-built Model
    • ◼
  • Using Existing Neural Net Architectures
    • ◼
  • Quiz 1

    • Working in the Framework

    ◼
  • Why Use Neural Networks?
    • ◼
  • Neural Nets as Differentiable Programs
    • ◼
  • LinearLayer; Layer Properties
    • ◼
  • Two-Class Classification
    • ◼
  • Three-Class Classification
    • ◼
  • Data Encoding; Training and Validation
    • ◼
  • Stacking Layers
    • ◼
  • Solving XOR with a Deep Network
    • ◼
  • Computational Graphs
    • ◼
  • Quiz 2
    • 4
    .
    Building Applications with the Neural Net Repository

    Image Applications

    ◼
  • Introducing the Neural Net Repository
    • ◼
  • Image and Video Classification
    • ◼
  • Semantic Segmentation
    • ◼
  • Object Detection
    • ◼
  • Image Captioning
    • ◼
  • Image Question Answering
    • ◼
  • Exploration: Mushroom Image Classifier
    • ◼
  • Feature Extraction
    • ◼
  • Generate Images from Text
    • ◼
  • Quiz 1

    • Text and Audio Applications

    ◼
  • Bidirectional “Encoder” Transformers
    • ◼
  • Character-Level and Word-Level Models
    • ◼
  • Exploration: Star Name Generation
    • ◼
  • Audio Identification
    • ◼
  • Speech to Text and Translation
    • ◼
  • Exploration: Audio Classifier
    • ◼
  • Quiz 2
    • 5
    .
    Programming with LLM Functions

    What Is a GPT?

    ◼
  • Tokens
    • ◼
  • Basic Layers of a GPT Model
    • ◼
  • Training the GPT Model
    • ◼
  • An Example Using GPT-3.5 Turbo
    • ◼
  • Quiz 1

    • Inside ChatGPT

    ◼
  • Some Neural Nets Groundwork
    • ◼
  • The Concept of Embeddings
    • ◼
  • ChatGPT Foundations, Part 1
    • ◼
  • ChatGPT Foundations, Part 2
    • ◼
  • The Fine-Tuning of ChatGPT
    • ◼
  • Quiz 2

    • LLM Programming

    ◼
  • A First Look at Chatbots
    • ◼
  • Setting Up Access to Models
    • ◼
  • Chat Notebooks
    • ◼
  • Personas from the Prompt Repository
    • ◼
  • Using the Definition Notebook
    • ◼
  • Prompt Engineering
    • ◼
  • Experimenting with Prompts
    • ◼
  • Dynamic Prompts
    • ◼
  • Adding Computational Tools
    • ◼
  • Using Tools
    • ◼
  • Non-Chat Uses of LLMs
    • ◼
  • Chain of Thought with LLMGraph
    • ◼
  • Model Configuration
    • ◼
  • Creating Custom Chat Interfaces
    • ◼
  • Asynchronous and Parallel Access
    • ◼
  • Quiz 3
    • 6
    .
    Deep Learning for Text Analysis

    Overview and the Chat Interface

    ◼
  • Pre-trained LLMs
    • ◼
  • The Chat Notebook Interface
    • ◼
  • Quiz 1

    • Machine Learning Concepts

    ◼
  • Machine Learning Concepts, Part 1
    • ◼
  • Machine Learning Concepts, Part 2
    • ◼
  • Machine Learning Concepts, Part 3
    • ◼
  • Quiz 2

    • Prompt Engineering

    ◼
  • Using LLMFunction in Prompts
    • ◼
  • Using Lists of Prompts
    • ◼
  • Using Examples in Prompts
    • ◼
  • Quiz 3

    • Multistep and Tool-Augmented Chat

    ◼
  • Augmenting Chat with Multistep
    • ◼
  • Using TextSummarize
    • ◼
  • Using Tools to Prevent Hallucination
    • ◼
  • Quiz 4
    • 7
    .
    Convolutional Networks for Image Computations

    Basics of Image Classification

    ◼
  • Overview and Human Visual System
    • ◼
  • Properties of Image Data
    • ◼
  • Network Encoders
    • ◼
  • Working with CIFAR-10 Dataset; Arrays and Tensors
    • ◼
  • Convolution Layers
    • ◼
  • ElementwiseLayer and ReLU
    • ◼
  • Pooling and Softmax Layer
    • ◼
  • Loss Layer and Cross Entropy
    • ◼
  • Quiz 1

    • Neural Net Training and Analysis

    ◼
  • Detecting and Avoiding Overfitting
    • ◼
  • Dropout Layers
    • ◼
  • Optical Illusions
    • ◼
  • Receptive Fields and Sensitivity Maps
    • ◼
  • Network Gradient Analysis
    • ◼
  • Image Feature Visualization
    • ◼
  • Quiz 2

    • Neural Net Design

    ◼
  • Inception Module
    • ◼
  • ResNets
    • ◼
  • U-Nets
    • ◼
  • EfficientNet: Squeeze & Expand
    • ◼
  • Transformers
    • ◼
  • Quiz 3

    • Image Applications

    ◼
  • Image Retrieval
    • ◼
  • Object Detection
    • ◼
  • Image Reconstruction
    • ◼
  • Cycle GAN
    • ◼
  • Image Segmentation
    • ◼
  • Quiz 4
    • 8
    .
    Deep Learning Applications for Audio and Video Applications

    Data Explanation

    ◼
  • Some Examples
    • ◼
  • Audio Net Encoders
    • ◼
  • Audio Data Augmentation
    • ◼
  • Video Net Encoder
    • ◼
  • Net Decoders
    • ◼
  • Build an Audio Classifier
    • ◼
  • Quiz 1

    • Net Architectures

    ◼
  • Simple Multilayer Perceptron
    • ◼
  • Convolution
    • ◼
  • Recurrence
    • ◼
  • Attention
    • ◼
  • Quiz 2

    • Applications

    ◼
  • Feature Extraction
    • ◼
  • Audio Identification
    • ◼
  • Speech Recognition
    • ◼
  • Video Denoising
    • ◼
  • Video Classification
    • ◼
  • Transfer Learning
    • ◼
  • Quiz 3