This book is a practical, application-focused guide to artificial intelligence and machine learning in neuroscience, designed to help readers use these methods without requiring advanced mathematics or deep technical prerequisites. It distinguishes itself by pairing each method with a neuroscience example and ready-to-use code, making it especially useful for students and researchers who want concise, applied instruction rather than a purely theoretical treatment.
A Practical Guide to Artificial Intelligence in Neuroscience covers the major tools used in contemporary data-driven neuroscience, from regression and classification to clustering, dimensionality reduction, neural networks, deep learning, fuzzy systems, and natural language processing. It shows how to move from raw brain data to clinically meaningful predictions and insights, without requiring advanced mathematics or computer science training. The chapters are organized to move from classical supervised methods through unsupervised learning and into advanced neural approaches, giving readers a coherent path from foundational statistical modeling to modern AI applications in brain and health research.
Designed for time-pressed graduate and undergraduate students in medicine, psychology, and health-related fields, as well as practicing neuroscientists,
A Practical Guide to Artificial Intelligence in Neuroscience bridges the gap between powerful modern AI
Chapter 1: Multiple Linear Regression.- Chapter 2: Logistic Regression (Binomial and Multinominal).- Chapter 3: Ordinal Logistic Regression.- Chapter 4: Poisson Regression and Negative Binomial Regression.- Chapter 5: Support Vector Machines (SVM).- Chapter 6: Decision Trees.- Chapter 7: Random Forests.- Chapter 8: Gradient Boosting Machines (GBM).- Chapter 9: Extreme Gradient Boosting Machines (XGBoost).- Chapter 10: K-Nearest Neighbour (KNN).- Chapter 11: Linear Discriminant Analysis (LDA).- Chapter 12: Quadratic Discriminant Analysis (QDA).- Chapter 13: K-Means Clustering.- Chapter 14: k-prototype Clustering.- Chapter 15: Hierarchical Clustering.- Chapter 16: Gaussian Mixture Model (GMM).- Chapter 17: Self-Organizing Maps (SOM).- Chapter 18: Principal Component Analysis (PCA).- Chapter 19: Nonlinear Principal Component Analysis.- Chapter 20: Independent Component Analysis (ICA).- Chapter 21: Neural Networks (NN).- Chapter 22: Deep Learning (DL).- Chapter 23: Fuzzy Neural Networks (FNN).- Chapter 24: Natural Language Processing (NLP).
Dr. Nader Fallah is an Associate Director of Artificial Intelligence at the Praxis Spinal Cord Institute and adjunct professor at Division of Neurology, Department of Medicine at University of British Columbia. He obtained his PhD in biostatistics from Tehran University of Medical Sciences in 2008. During his PhD, he was a fellow visitor at the Abdus Salam International Center for Theoretical Physics, Italy in 2003, and at Dalhousie University in 2006-2007. Upon completion of his PhD, he continued his work at Dalhousie University as a postdoctoral fellow and later completed second postdoctoral training at University of British Columbia both in neuroscience.
His core area of interest is the application of artificial intelligence and machine learning in neuroscience. His long-standing collaborations with physicians and researchers have resulted in 3 books and more than 100 publications in peer-reviewed biostatistics, machine learning, and medical journals. He leads a team of machine learning experts and biostatisticians focused on developing and applying AI techniques and statistical methods to improve the quality of life of people with spinal cord injuries and Alzheimer s diseases.
