No upcoming dates
Model relationships in neuroscience data while checking whether results generalize. Explore data preparation, normalization, cross-validation, model comparison, neural networks, and reproducible training workflows.
Expected and helpful background knowledge for joining an event on this topic.
Machine learning can reveal linear and nonlinear relationships among neural measurements, experimental conditions, and behavior. Drawing reliable conclusions requires more than fitting a model: data representation, normalization, validation design, model comparison, and diagnostic checks all influence whether apparent performance generalizes to new data.
Machine learning is most useful in research when the path from data preparation to model comparison is clear. Normalization choices, cross-validation design, performance baselines, and diagnostic checks all affect whether a model generalizes beyond its training data. This topic connects these foundations to neural network modeling while emphasizing reproducible code and healthy skepticism about model performance.
For this approach, familiarity with Python and Jupyter notebooks is required. Consult the event page for its specific setup and requirements.
Using real neuroscience datasets, you will prepare and normalize inputs, evaluate models with cross-validation, and compare linear and nonlinear approaches using Scikit-learn and PyTorch. You will then explore feedforward, recurrent, and convolutional neural networks, as well as data augmentation and regularization. You will also use object-oriented programming to organize scalable and efficient training pipelines.
Explore upcoming dates and details from previous events.
Deep learning (DL) has quickly become one of the most popular analysis tools in neuroscience. This three-day, hands-on workshop introduces the core principles and practical …
Our view of the tools and practices relevant to this topic. Recommendation and teaching availability are separate.
Provisional positions are editorial proposals awaiting group review.
Select a point or an item below to read our view.
No items match this view.
Check important behavior automatically so research code can be changed with confidence.
Practices · Teaching
0 topics with recorded teaching · 0 recorded and scheduled offerings
Tests make scientific assumptions and expected behavior explicit, and help catch regressions as analysis code develops.
Covered in our robust software and AI-assisted development topics; individual offerings are not yet attributed to this practice.
0 past offerings · 0 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: AI-Assisted Software DevelopmentMachine Learning(M)EEG AnalysisNeural Spike AnalysisRobust and Reusable Software
Check the shape, types, units, and assumptions of research data before using it.
Practices · Teaching
0 topics with recorded teaching · 0 recorded and scheduled offerings
Explicit validation turns data assumptions into checks that can catch missing values, inconsistent metadata, and unexpected inputs before analysis.
Covered through data organization and robust software topics; individual offerings are not yet attributed to this practice.
0 past offerings · 0 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: Programming and Data AcquisitionAI-Assisted Software DevelopmentArrays and Numerical ComputingCalcium Imaging AnalysisDataframes and StatisticsLocal Field Potential (LFP) AnalysisMachine Learning(M)EEG AnalysisNeural Spike AnalysisRobust and Reusable Software
Interactive computing environment combining code, visualizations, and narrative text
Tools & platforms · Teaching
6 topics with recorded teaching · 17 recorded and scheduled offerings
Jupyter notebooks allow you to combine code, results, and explanations in a single document. This makes them perfect for exploratory data analysis, teaching, and creating reproducible research workflows. You can iterate quickly, visualize results inline, and document your thought process as you work.
Recorded in topic offerings; consult the dated event links for availability.
15 past offerings · 2 upcoming offerings
Related themes: Scientific Computing
Related topics: Arrays and Numerical ComputingAutomating Research WorkflowsDataframes and StatisticsDeveloper EnvironmentMachine LearningRobust and Reusable SoftwareWebsite Development
The fundamental package for scientific computing with Python
Libraries · Teaching
8 topics with recorded teaching · 26 recorded and scheduled offerings
NumPy is the foundation of the scientific Python ecosystem. It provides powerful n-dimensional array objects and tools for working with these arrays. Nearly every scientific Python package builds on NumPy, making it essential for data analysis, numerical computing, and scientific research.
Recorded in topic offerings; consult the dated event links for availability.
21 past offerings · 5 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: AI-Assisted Software DevelopmentArrays and Numerical ComputingCalcium Imaging AnalysisDataframes and StatisticsLocal Field Potential (LFP) AnalysisMachine Learning(M)EEG AnalysisNeural Spike AnalysisRobust and Reusable Software
General-purpose programming language widely used for scientific computing and research software.
Languages & frameworks · Teaching
10 topics with recorded teaching · 33 recorded and scheduled offerings
Python combines a readable language with a mature scientific ecosystem, making it a practical default for research data analysis, automation, and teaching.
Recorded in topic offerings; consult the dated event links for availability.
26 past offerings · 7 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: Programming and Data AcquisitionAI-Assisted Software DevelopmentArrays and Numerical ComputingAutomating Research WorkflowsCalcium Imaging AnalysisDataframes and StatisticsDeveloper EnvironmentLocal Field Potential (LFP) AnalysisMachine Learning(M)EEG AnalysisNeural Spike AnalysisRobust and Reusable Software
Record and reproduce the software environment used for an analysis or application.
Practices · Teaching
0 topics with recorded teaching · 0 recorded and scheduled offerings
Declared dependencies and lock files help collaborators rerun analyses and distinguish environment changes from changes in scientific results.
Covered through our computing environment and research workflow topics; individual offerings are not yet attributed to this practice.
0 past offerings · 0 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: AI-Assisted Software DevelopmentArrays and Numerical ComputingAutomating Research WorkflowsCalcium Imaging AnalysisDataframes and StatisticsDeveloper EnvironmentLocal Field Potential (LFP) AnalysisMachine LearningRobust and Reusable Software
Machine learning library for Python with tools for classification, regression, clustering, and dimensionality reduction
Libraries · Teaching
3 topics with recorded teaching · 6 recorded and scheduled offerings
Scikit-learn provides a consistent, easy-to-use interface for machine learning in Python. It's perfect for analyzing neuroscience data: clustering neurons, reducing dimensionality of neural responses, and classifying behavioral states.
Recorded in topic offerings; consult the dated event links for availability.
4 past offerings · 2 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: AI-Assisted Software DevelopmentMachine Learning(M)EEG AnalysisNeural Spike Analysis
Scientific computing library providing optimization, signal processing, and statistical functions
Libraries · Teaching
5 topics with recorded teaching · 14 recorded and scheduled offerings
SciPy builds on NumPy to provide a comprehensive collection of algorithms for scientific computing. Its signal processing tools are essential for analyzing neural recordings, while its optimization and statistical functions support data analysis and modeling across neuroscience research.
Recorded in topic offerings; consult the dated event links for availability.
9 past offerings · 5 upcoming offerings
Related themes: Neural Data AnalysisScientific Computing
Related topics: AI-Assisted Software DevelopmentArrays and Numerical ComputingCalcium Imaging AnalysisLocal Field Potential (LFP) AnalysisMachine Learning(M)EEG AnalysisNeural Spike Analysis
GPU-accelerated array library with a NumPy-like interface.
Libraries · Teaching
1 topics with recorded teaching · 2 recorded and scheduled offerings
CuPy helps move suitable NumPy-style workloads onto GPUs with familiar array operations.
Recorded in topic offerings; consult the dated event links for availability.
1 past offerings · 1 upcoming offerings
Related themes: Scientific Computing
Related topics: Arrays and Numerical ComputingMachine LearningRobust and Reusable Software
Python library for composable transformations, automatic differentiation, and accelerated array computing.
Libraries · Not currently taught
0 topics with recorded teaching · 0 recorded and scheduled offerings
JAX is useful for high-performance numerical work that benefits from compilation, vectorization, and automatic differentiation.
Relevant to the topic landscape; no explicit recorded offering is currently attributed to this item.
0 past offerings · 0 upcoming offerings
Related themes: Scientific Computing
Related topics: Arrays and Numerical ComputingMachine Learning
Python just-in-time compiler for accelerating numerical functions.
Libraries · Teaching
1 topics with recorded teaching · 2 recorded and scheduled offerings
Numba can speed up numerical Python code while keeping performance work close to familiar Python and NumPy-style code.
Recorded in topic offerings; consult the dated event links for availability.
1 past offerings · 1 upcoming offerings
Related themes: Scientific Computing
Related topics: Arrays and Numerical ComputingMachine LearningRobust and Reusable Software
Deep learning framework with dynamic computation graphs and GPU acceleration
Languages & frameworks · Teaching
1 topics with recorded teaching · 1 recorded and scheduled offerings
PyTorch offers an intuitive, Pythonic approach to building neural networks with excellent debugging capabilities. Its dynamic computation graphs make it ideal for research, while its performance and ecosystem make it production-ready. It's become the standard for neuroscience modeling and deep learning research.
Recorded in topic offerings; consult the dated event links for availability.
1 past offerings · 0 upcoming offerings
Related themes: Scientific Computing
Related topics: Machine Learning
For tutoring, collaboration, or follow-up support, contact the team. We are happy to help you connect workshop ideas with your own research practice.
iBOTS
