NeuroAI Labs Workbook

Hands-On Computational Exercises

Author

Richard Young, Ph.D.

Published

June 26, 2026

NeuroAI Labs Workbook

Hands-on computational neuroscience: where code meets brain science

Welcome to the Hands-On Computational Companion to The NeuroAI Handbook.

About This Workbook

This workbook contains computational labs that implement the concepts, algorithms, and models presented in the main textbook. Each lab provides:

Learning objectives aligned with textbook chapters
Python implementations of key algorithms and simulations
Hands-on exercises with guided instructions
Challenge problems for deeper exploration
Discussion questions connecting neuroscience and AI

How to Use This Workbook

1. Prerequisites - Read the corresponding chapter in the main textbook first - Ensure Python environment is set up (see main book setup instructions) - Have NumPy, Matplotlib, SciPy, and scikit-learn installed

2. Workflow - Work through each lab section sequentially - Run all code cells and examine outputs - Complete the exercises embedded throughout - Attempt the challenge problems - Reflect on the discussion questions

3. Lab Structure Each lab mirrors a chapter from the main textbook and includes: - Setup and imports - Step-by-step implementations - Visualizations and analysis - Exercises and challenges

Labs Overview

Labs are organized to match the textbook structure:

Part I (Labs 1-6): Neuroscience foundations and brain-inspired models
Part II (Labs 7-11): Mathematical frameworks and computational methods
Part III (Labs 12-13): Machine learning and deep learning
Part IV (Labs 14-16): Sequence models, LLMs, and multimodal AI
Part V (Labs 17-19): Bridging biological and artificial intelligence
Part VI (Labs 20-27): Advanced applications and future directions

Required Software

# Activate virtual environment
source ../venv/bin/activate

# Verify key packages
python -c "import numpy, matplotlib, scipy, sklearn; print('All packages ready!')"

Getting Help

Main textbook: Theoretical foundations and explanations
Appendix 91: Math and Python refresher
Appendix 92: Dataset catalogue
Appendix 93: Google Colab setup

Learning Goals

By completing these labs, you will:

Implement classic neuroscience models (LIF neurons, place cells, grid cells)
Build machine learning pipelines for neural data analysis
Create deep learning models inspired by brain architecture
Apply information theory to neural coding
Conduct causal inference on neuroscience data
Develop bio-inspired AI algorithms

Ready to begin? Start with the lab that corresponds to your current chapter in the main textbook, or work through sequentially from Lab 1.

# NeuroAI Labs Workbook {.unnumbered} ![Hands-on computational neuroscience: where code meets brain science](images/workbook_cover.png){width="100%"} Welcome to the **Hands-On Computational Companion** to *The NeuroAI Handbook*. ## About This Workbook This workbook contains computational labs that implement the concepts, algorithms, and models presented in the main textbook. Each lab provides: - **Learning objectives** aligned with textbook chapters - **Python implementations** of key algorithms and simulations - **Hands-on exercises** with guided instructions - **Challenge problems** for deeper exploration - **Discussion questions** connecting neuroscience and AI ## How to Use This Workbook **1. Prerequisites** - Read the corresponding chapter in the main textbook first - Ensure Python environment is set up (see main book setup instructions) - Have NumPy, Matplotlib, SciPy, and scikit-learn installed **2. Workflow** - Work through each lab section sequentially - Run all code cells and examine outputs - Complete the exercises embedded throughout - Attempt the challenge problems - Reflect on the discussion questions **3. Lab Structure** Each lab mirrors a chapter from the main textbook and includes: - Setup and imports - Step-by-step implementations - Visualizations and analysis - Exercises and challenges ## Labs Overview Labs are organized to match the textbook structure: - **Part I (Labs 1-6):** Neuroscience foundations and brain-inspired models - **Part II (Labs 7-11):** Mathematical frameworks and computational methods - **Part III (Labs 12-13):** Machine learning and deep learning - **Part IV (Labs 14-16):** Sequence models, LLMs, and multimodal AI - **Part V (Labs 17-19):** Bridging biological and artificial intelligence - **Part VI (Labs 20-27):** Advanced applications and future directions ## Required Software ```bash # Activate virtual environment source ../venv/bin/activate # Verify key packages python -c "import numpy, matplotlib, scipy, sklearn; print('All packages ready!')" ``` ## Getting Help - **Main textbook:** Theoretical foundations and explanations - **Appendix 91:** Math and Python refresher - **Appendix 92:** Dataset catalogue - **Appendix 93:** Google Colab setup ## Learning Goals By completing these labs, you will: 1. Implement classic neuroscience models (LIF neurons, place cells, grid cells) 2. Build machine learning pipelines for neural data analysis 3. Create deep learning models inspired by brain architecture 4. Apply information theory to neural coding 5. Conduct causal inference on neuroscience data 6. Develop bio-inspired AI algorithms --- **Ready to begin?** Start with the lab that corresponds to your current chapter in the main textbook, or work through sequentially from Lab 1.