This lesson describes the principles underlying functional magnetic resonance imaging (fMRI), diffusion-weighted imaging (DWI), tractography, and parcellation. These tools and concepts are explained in a broader context of neural connectivity and mental health.
This lesson briefly goes over the outline of the Neuroscience for Machine Learners course.
This lesson delves into the the structure of one of the brain's most elemental computational units, the neuron, and how said structure influences computational neural network models.
In this lesson you will learn how machine learners and neuroscientists construct abstract computational models based on various neurophysiological signalling properties.
This lesson goes over some examples of how machine learners and computational neuroscientists go about designing and building neural network models inspired by biological brain systems.
This lesson characterizes different types of learning in a neuroscientific and cellular context, and various models employed by researchers to investigate the mechanisms involved.
In this lesson, you will learn about different approaches to modeling learning in neural networks, particularly focusing on system parameters such as firing rates and synaptic weights impact a network.
In this lesson, you will learn about some of the many methods to train spiking neural networks (SNNs) with either no attempt to use gradients, or only use gradients in a limited or constrained way.
In this lesson, you will learn how to train spiking neural networks (SNNs) with a surrogate gradient method.
This lesson gives an introduction to the central concepts of machine learning, and how they can be applied in Python using the scikit-learn package.
This is a continuation of the talk on the cellular mechanisms of neuronal communication, this time at the level of brain microcircuits and associated global signals like those measureable by electroencephalography (EEG). This lecture also discusses EEG biomarkers in mental health disorders, and how those cortical signatures may be simulated digitally.
This lecture covers the rationale for developing the DAQCORD, a framework for the design, documentation, and reporting of data curation methods in order to advance the scientific rigour, reproducibility, and analysis of data.
The Medical Informatics Platform (MIP) is a platform providing federated analytics for diagnosis and research in clinical neuroscience research. The federated analytics is possible thanks to a distributed engine that executes computations and transfers information between the members of the federation (hospital nodes). In this talk the speaker will describe the process of designing and implementing new analytical tools, i.e. statistical and machine learning algorithms. Mr. Sakellariou will further describe the environment in which these federated algorithms run, the challenges and the available tools, the principles that guide its design and the followed general methodology for each new algorithm. One of the most important challenges which are faced is to design these tools in a way that does not compromise the privacy of the clinical data involved. The speaker will show how to address the main questions when designing such algorithms: how to decompose and distribute the computations and what kind of information to exchange between nodes, in order to comply with the privacy constraint mentioned above. Finally, also the subject of validating these federated algorithms will be briefly touched.
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.
While the previous lesson in the Neuro4ML course dealt with the mechanisms involved in individual synapses, this lesson discusses how synapses and their neurons' firing patterns may change over time.