Supplementary Materials for A Large-Scale Model of the Functioning Brain

By Chris Eliasmith, T. Stewart, Xuan Choo, Trevor Bekolay, Travis DeWolf, Yichuan Tang, Daniel Rasmussen. 2012

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Neuroscience

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, background): “Rasmussen, D. (2012) A large-scale model of the functioning brain.”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “Neural models range from small directed graphs in which nodes are simple functions of the input, to complex and some-times large spiking neural models and bio-physical models (Markram, 2006, 2012; Eliasmith et al., 2012).”
Direct-fit to nature: an evolutionary perspective on biological (and artificial) neural networks (2019, background): “Modern ANNs have exposed the power and versatility of this encoding scheme: a variety of seemingly distinct “tasks” can be performed by interpolating over a single high-dimensional embedding space (e.g., Eliasmith et al., 2012; O’Toole et al., 2018; Radford et al., 2019; Raffel et al., 2019).”
Event-Based Vision: A Survey (2019, methodology): “It is programmed using Nengo [238] and implements the Neural Engineering Framework [239].”
SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks (2017, methodology): “…using spiking networks, they still use effectively a rate-based approach in which a given input activity vector is interpreted as the firing rate of a set of input neurons (Eliasmith et al., 2012; Diehl & Cook, 2015; Guergiuev et al., 2016; Neftci et al., 2016; Mesnard, Gerstner, & Brea, 2016).”
Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations (2014, background): “5 10(6) neurons) 9000 times slower than a real mouse brain operates [2], while using 40 000 times more power (400 W versus 10 mW [3]).”
Artificial Neural Networks for Neuroscientists: A Primer (2020, methodology): “As computational models of visual systems, convolutional networks can model complex, high-dimensional inputs to downstream areas, useful for large-scale models using pixel-based visual inputs [Eliasmith et al., 2012].”
Deep Learning With Spiking Neurons: Opportunities and Challenges (2018, methodology): “An alternative method is to use the Neural Engineering Framework (Eliasmith and Anderson, 2004) to convert restricted Boltzmann machines into spiking networks (Eliasmith et al., 2012).”
Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems (2014, background): “This is a concrete example showing how neuromorphic systems, built using variable and imprecise circuits, can indeed be configured to express cognitive abilities comparable to those described in [21] and [30].”
What must a global theory of cortex explain? (2014, methodology): “We shall make references to some recent examples [6 ,7 ,8 ,9 ] in order to contrast some of the currently pursued alternatives.”
Enhanced image classification with a fast-learning shallow convolutional neural network (2015, methodology): “The fast training method we use has been developed independently several times [6–9] and has gained increasing recognition in recent years—see [10–14] for recent reviews.”
Spiking Deep Networks with LIF Neurons (2015, background): “There has recently been considerable effort to take deep ANNs and make them more biologically plausible by introducing neural “spiking” [8, 9, 10, 11, 12, 13], such that connected nodes in the network transmit information via instantaneous single bits (spikes), rather than transmitting real-valued…”
Deep Learning in Spiking Neural Networks (2018, background): “Spiking networks consisting of many LIF neurons equipped by spike-based synaptic plasticity rules have shown success in different pattern recognition tasks [128], [129].”
The atoms of neural computation (2014, background): “…gating of subsets of large-scale attractor networks linking many cortical regions Higher cortical areas Holographic reduced representations (Eliasmith et al., 2012) Circular convolution applied to population coded vector representations in cortical working memory buffers, gated by thalamic…”