Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems

By Chris Eliasmith, Charles H. Anderson. IEEE Transactions on Neural Networks, 2004

860 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6f093c5ec100804c98a25d9831b025949e5cb78e

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Supplementary Materials for A Large-Scale Model of the Functioning Brain (2012, neutral): “Serial working memory A3 [3 2 4 3 5] ? A3 [4 2 5 3 4 2] ? 3 2 4 3 5 4 2 5 – 4 2 Counting A4 [3] [2] ? A4 [0] [7] ? 5 7 Question answering A5 [4 3 8 6] [K] [4] ? A5 [4 3 8 6] [P] [4] ? 1 6 Rapid variable creation A6 [3312] [12 ][3392] [92] [3362] [62] [3342] ? A6 [342] [2 ][345] [5] [347] [7] [340] ?”
Toward an Integration of Deep Learning and Neuroscience (2016, methodology): “Neural models of working memory can store not only scalar variables (Seung, 1998), but also high-dimensional vectors (Eliasmith and Anderson, 2004; Eliasmith et al., 2012) or sequences of vectors (Choo and Eliasmith, 2010).”
Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE) (2018, background): “neuron is required. This enables the algorithm to scale spatially as O(N). The local classiﬁer in DECOLLE acts like an encoder-decoder layer in the ﬂavor of linear readouts in reservoir type networks [8, 15, 23]. The key difference with DECOLLE is that the encoder weights are trained, whereas the de”
Probabilistic population codes for Bayesian decision making (2008, result): “Nonetheless, the ﬁnding that the width of the population activity is invariant over time would be consistent with our model, while ruling out codes in which neural activities are proportional to probability (Barber et al., 2003; Eliasmith and Anderson, 2003).”
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.”
Probabilistic brains: knowns and unknowns (2013, neutral): “63,64 for variations of these ideas).”
Linking Connectivity, Dynamics, and Computations in Low-Rank Recurrent Neural Networks. (2017, neutral): “, 2007) and FORCE learning (Sussillo and Abbott, 2009), and similarly within the Neural Engineering Framework (Eliasmith and Anderson, 2004), computations are implemented through feedback loops from readout units to the bulk of the network.”
CREATIVE COMBINATION OF REPRESENTATIONS: SCIENTIFIC DISCOVERY AND TECHNOLOGICAL INVENTION (2010, background): “From the perspective of current work in theoretical neuroscience, concepts and other representations are patterns of firing activity in neural populations (Dayan and Abbott, 2000; Eliasmith and Anderson, 2003; O’Reilly and Munakata, 2000; Thagard, 2010a).”
Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook (2021, methodology): “The neural engineering framework (NEF) [19] and other related capabilities are supported through the Nengo toolchain [20] from Applied Brain Research.”
Nengo: a Python tool for building large-scale functional brain models (2014, methodology): “TheNeural Engineering Framework (NEF; Eliasmith and Anderson, 2003) provides a set of methods for building biologically plausible models based on a functional speciﬁcation of a neural system.”
Eye smarter than scientists believed: Neural computations in circuits of the retina (2010, positive): “This requires broadening the concept of “explicit”, and we suggest a criterion that has been used effectively in the past (Marder and Abbott, 1995; Eliasmith and Anderson, 2002; Shamir and Sompolinsky, 2006): In a distributed representation, the answer of interest should be obtainable through linear”
Theorizing Flow and Media Enjoyment as Cognitive Synchronization of Attentional and Reward Networks (2009, background): “It describes a mechanism by which complexity arises in nature and has been Communication Theory 19 (2009) 397–422 © 2009 International Communication Association 409 found to exist in a wide variety of dynamic systems (for a review, see Eliasmith & Anderson, 2003).”
The atoms of neural computation (2014, background): “An incomplete list of steps that might be in the right direction include the following: • The semantic pointer architecture unified network (SPAUN) system (Eliasmith et al., 2012) (Eliasmith & Anderson, 2004), for representation and transformation of variables in neuronal populations.”
Hierarchical Bayesian inference in the visual cortex. (2003, neutral): “This idea would seem on the surface to be related to the ideas of Zemel 33 and Eliasmith and Anderson 34 on population coding and decoding.”
Neuromorphic photonic networks using silicon photonic weight banks (2016, methodology): “These architectures’ adherence to neural network models unlocks a wealth of metrics [26], algorithms [27, 28], tools [29, 30], and benchmarks [31] developed speciﬁcally for neural networks.”
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.”