Neuroscience for Machine Learners (Neuro4ML)

This lesson gives a brief introduction to the course Neuroscience for Machine Learners (Neuro4ML). 

This lesson briefly goes over the outline of the Neuroscience for Machine Learners course. 

This lesson covers the history of neuroscience and machine learning, and the story of how these two seemingly disparate fields are increasingly merging. 

In this lesson, you will learn about the current challenges facing the integration of machine learning and neuroscience. 

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. 

Following the previous lesson on neuronal structure, this lesson discusses neuronal function, particularly focusing on spike triggering and propogation. 

In this lesson you will learn how machine learners and neuroscientists construct abstract computational models based on various neurophysiological signalling properties. 

In this lesson, you will learn about some typical neuronal models employed by machine learners and computational neuroscientists, meant to imitate the biophysical properties of real neurons. 

This lesson contains practical exercises which accompanies the first few lessons of the Neuroscience for Machine Learners (Neuro4ML) course. 

This lesson goes over the basic mechanisms of neural synapses, the space between neurons where signals may be transmitted. 

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. 

Whereas the previous two lessons described the biophysical and signalling properties of individual neurons, this lesson describes properties of those units when part of larger networks. 

In this lesson, you will learn about how machine learners and computational neuroscientists design and build models of neuronal synapses. 

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 introduces some practical exercises which accompany the Synapses and Networks portion of this Neuroscience for Machine Learners course. 

In this lesson, you will learn about the connectome, the collective system of neural pathways in an organism, with a closer look at the neurons, synapses, and connections of particular species. 

This lesson delves into the human nervous system and the immense cellular, connectomic, and functional sophistication therein. 

This lesson introduces the practical exercises which accompany the previous lessons on animal and human connectomes in the brain and nervous system. 

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. 

This lesson describes spike timing-dependent plasticity (STDP), a biological process that adjusts the strength of connections between neurons in the brain, and how one can implement or mimic this process in a computational model. You will also find links for practical exercises at the bottom of this page. 

In this lesson, you will learn more about some of the issues inherent in modeling neural spikes, approaches to ameliorate these problems, and the pros and cons of these approaches. 

 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 explores how researchers try to understand neural networks, particularly in the case of observing neural activity. 

As the previous lesson of this course described how researchers acquire neural data, this lesson will discuss how to go about interpreting and analysing the data. 

In this lesson you will learn about the motivation behind manipulating neural activity, and what forms that may take in various experimental designs. 

This video briefly goes over the exercises accompanying Week 6 of the Neuroscience for Machine Learners (Neuro4ML) course, Understanding Neural Networks.

In this lesson, you will learn about one particular aspect of decision making: reaction times. In other words, how long does it take to take a decision based on a stream of information arriving continuously over time?

This video gives a brief introduction to Neuro4ML's lessons on neuromorphic computing - the use of specialized hardware which either directly mimics brain function or is inspired by some aspect of the way the brain computes. 

In this lesson, you will learn in more detail about neuromorphic computing, that is, non-standard computational architectures that mimic some aspect of the way the brain works. 

This video provides a very quick introduction to some of the neuromorphic sensing devices, and how they offer unique, low-power applications.

In this lesson, you will hear about some of the open issues in the field of neuroscience, as well as a discussion about whether neuroscience works, and how can we know?

This lesson discusses a gripping neuroscientific question: why have neurons developed the discrete action potential, or spike, as a principle method of communication?