Skip to main content

Optimization for machine learning - Day 02 lecture of the Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 34:52
Speaker: : Moritz Wolter

Linear Algebra for Machine Learning - Day 03 lecture of the Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 57.45
Speaker: : Moritz Wolter

Support Vector Machines -  Day 06 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 53.39
Speaker: : Elena Trunz

Decision Trees and Random Forests -  Day 07 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 1:15:39
Speaker: : Elena Trunz

Clustering and Density Estimation -  Day 08 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 59:35
Speaker: : Elena Trunz

Dimensionality Reduction -  Day 09 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 51:02
Speaker: : Elena Trunz

Introduction to Neural Networks -  Day 10 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 54:12
Speaker: : Moritz Wolter

Introduction to Convolutional Neural Networks  -  Day 11 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 42:07
Speaker: : Moritz Wolter

Initialization, Optimization, and Regularization  -  Day 12 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 42:07
Speaker: : Moritz Wolter

U-Nets for medical Image-Segmentation  -  Day 13 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 16:45
Speaker: : Moritz Wolter

Sequence Processing -  Day 15 lecture of the  Foundations of Machine Learning in Python course.

High-Performance Computing and Analytics Lab, University of Bonn

Difficulty level: Advanced
Duration: 47:45
Speaker: : Moritz Wolter

This lecture presents an overview of functional brain parcellations, as well as a set of tutorials on bootstrap agregation of stable clusters (BASC) for fMRI brain parcellation.

Difficulty level: Advanced
Duration: 50:28
Speaker: : Pierre Bellec

This lesson provides an introduction to biologically detailed computational modelling of neural dynamics, including neuron membrane potential simulation and F-I curves. 

Difficulty level: Intermediate
Duration: 8:21
Speaker: : Mike X. Cohen

In this lesson, users learn how to use MATLAB to build an adaptive exponential integrate and fire (AdEx) neuron model. 

Difficulty level: Intermediate
Duration: 22:01
Speaker: : Mike X. Cohen

In this lesson, users learn about the practical differences between MATLAB scripts and functions, as well as how to embed their neuronal simulation into a callable function.  

Difficulty level: Intermediate
Duration: 11:20
Speaker: : Mike X. Cohen

This lesson teaches users how to generate a frequency-current (F-I) curve, which describes the function that relates the net synaptic current (I) flowing into a neuron to its firing rate (F). 

Difficulty level: Intermediate
Duration: 20:39
Speaker: : Mike X. Cohen

This lesson is a general overview of overarching concepts in neuroinformatics research, with a particular focus on clinical approaches to defining, measuring, studying, diagnosing, and treating various brain disorders. Also described are the complex, multi-level nature of brain disorders and the data associated with them, from genes and individual cells up to cortical microcircuits and whole-brain network dynamics. Given the heterogeneity of brain disorders and their underlying mechanisms, this lesson lays out a case for multiscale neuroscience data integration.

Difficulty level: Intermediate
Duration: 1:09:33
Speaker: : Sean Hill

In this tutorial on simulating whole-brain activity using Python, participants can follow along using corresponding code and repositories, learning the basics of neural oscillatory dynamics, evoked responses and EEG signals, ultimately leading to the design of a network model of whole-brain anatomical connectivity. 

Difficulty level: Intermediate
Duration: 1:16:10
Speaker: : John Griffiths

This lesson breaks down the principles of Bayesian inference and how it relates to cognitive processes and functions like learning and perception. It is then explained how cognitive models can be built using Bayesian statistics in order to investigate how our brains interface with their environment. 

This lesson corresponds to slides 1-64 in the PDF below. 

Difficulty level: Intermediate
Duration: 1:28:14

This is a tutorial on designing a Bayesian inference model to map belief trajectories, with emphasis on gaining familiarity with Hierarchical Gaussian Filters (HGFs).

 

This lesson corresponds to slides 65-90 of the PDF below. 

Difficulty level: Intermediate
Duration: 1:15:04
Speaker: : Daniel Hauke