Machine Learning & Deep Learning for Neuroscience

About the Course

A 12-week instructor-guided course on the NeuroAI track, running from October 18 2026 to January 3, 2027. It builds systematically from machine-learning foundations through neural networks and deep learning for neural data, and closes with representation learning and a first look at modern architectures.

COURSE DATE October 18th, 2026 – January 3rd, 2027

DURATION 12 weeks · 12 live sessions

SCHEDULE Sunday evenings

LEVEL Basic → Advanced

REGISTER NOW

Course Curriculum

MODULE 01 Weeks 1–3 — Machine Learning Foundations

MODULE 01 3 Lessons

Machine Learning Foundations

Week 1 · Introduction to Machine Learning for Neuroscience — supervised, unsupervised and reinforcement learning; features, targets and datasets. Lab: Python/Colab orientation; loading and visualizing a simple neuroscience dataset
Week 2 · Regression and Classification — linear regression, logistic regression and performance measures. Lab: predicting a continuous neural/behavioural variable; classifying experimental conditions
Week 3 · Classical ML Methods — SVM, decision trees, random forests and k-nearest neighbours. Lab: compare multiple classifiers on the same neuroscience dataset

MODULE 02 Weeks 4–5 — Unsupervised Learning and Reliable Evaluation

MODULE 02 2 Lessons

Unsupervised Learning and Reliable Evaluation

Week 4 · Clustering and Dimensionality Reduction — k-means, hierarchical clustering, PCA and visualization. Lab: PCA of neural population, EEG or behavioural data; clustering subjects or trials
Week 5 · Validation, Generalization and Data Leakage — train/validation/test splits, cross-validation, regularization and class imbalance. Lab: build a leakage-free pipeline; interpret confusion matrices, ROC curves and errors

MODULE 03 Weeks 6–8 — Neural Networks and Learning

MODULE 03 3 Lessons

Neural Networks and Learning

Week 6 · From Biological Neurons to Artificial Networks — perceptrons, multilayer networks, weights, activations and loss functions. Lab: build a small neural network from first principles
Week 7 · How Artificial Networks Learn — gradient descent and backpropagation. Lab: step-by-step backpropagation; train an MLP in PyTorch or TensorFlow
Week 8 · Biological Learning and Artificial Learning — Hebbian learning, STDP and biological plausibility. Lab: simulate Hebbian learning and STDP; compare them with backpropagation

MODULE 04 Weeks 9–10 — Deep Learning for Neural Data

MODULE 04 2 Lessons

Deep Learning for Neural Data

Week 9 · Convolutional Neural Networks — convolution, feature hierarchies and visual processing. Lab: train a CNN on neural images, behavioural video frames or related image data
Week 10 · Recurrent Neural Networks — RNNs, LSTMs and GRUs for temporal neural signals. Lab: classify or predict EEG, spike-train or other time-series data

MODULE 05 Weeks 11–12 — Representation Learning and Modern Architectures

MODULE 05 2 Lessons

Representation Learning and Modern Architectures

Week 11 · Representation and Generative Learning — autoencoders and variational autoencoders; introduction to LFADS. Lab: build an autoencoder; visualize latent representations of neural data
Week 12 · Modern Extensions and Project Presentations — transformers, graph neural networks, self-supervised learning and generative models. Lab: short guided demonstrations; learner project presentations and instructor feedback

Each week combines about 30–45 minutes of recorded preparatory material, a 60–75 minute live conceptual class, a 45–60 minute guided tutorial, a structured practice notebook, a short quiz or submission, and discussion with instructor support through the Neurovidya course space. Learners do not merely hear about methods — they repeatedly apply them to neuroscience data and receive feedback.

Meet Your Instructor

Dr. Chandra Sekhar Vorugunti

Lead Computer Vision Engineer · Visiting Faculty, Professor of Practice & Senior Mentor

Dr. Chandra Sekhar Vorugunti completed his PhD from IIIT SriCity in deep learning, with visiting scholar stints at IIT Madras, IIT Tirupati, and IIT Indore. He has 14+ years of IT experience, 125+ publications at premier venues including ICDAR, IJCB, WACV, CVPR-W, and ICCV-W, and has delivered 100+ sessions across IITs and NITs. He serves as Visiting Faculty at BITS-Pilani, IIT Tirupati, and IISER Bhopal, and as Professor of Practice at Woxsen University, Krea University, Sathya Sai University, and IIITDM Jabalpur.

View Profile

About

Neurogati

Incubated at IIT Madras, Neurogati was born from a shared vision to integrate multiple dimensions of neurotechnology into a single, comprehensive system. Our founders believed that a more precise understanding of the brain-rooted in the powerful combination of AI, Computational Neuroscience, and Technology, could unlock earlier diagnoses, smarter therapies, and more intuitive support for those facing neurological disorders, neurodiversity, and the challenges of aging.

About

Neurovidya

Neurovidya is Neurogati's dedicated education and training ecosystem for neuroscience. It brings courses, workshops, and learning resources into one place so learners can progress from core ideas to applied skills. The platform is designed to translate complex neural concepts without losing scientific rigour. Learners can build foundations, explore computational and experimental methods, and connect neuroscience with AI, engineering, medicine, psychology, and research.

APPLICATIONS NOW OPEN

Machine Learning & Deep Learning for Neuroscience

A 12-week instructor-guided course on the NeuroAI track, running from October 18 2026 to January 3, 2027. It builds systematically from machine-learning foundations through neural networks and deep learning for neural data, and closes with representation learning and a first look at modern architectures.

REGISTER NOW