How to Build a Brain: A Neural Architecture for Biological Cognition

By Chris Eliasmith. 2013

493 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Neuroscience

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

In Neuroscience

Citations in the corpus

Neural Turing Machines (2014, background): “Modeling studies of working memory range from those that consider how biophysical circuits could implement persistent neuronal ﬁring (Wang, 1999) to those that try to solve explicit tasks (Hazy et al., 2006) (Dayan, 2008) (Eliasmith, 2013).”
Deep learning in neural networks: An overview (2014, neutral): “A spiking DBN with about 250,000 neurons (as part of a larger NN; Eliasmith, 2013; Eliasmith et al., 2012) achieved 6% error rate on MNIST; compare similar results with a spiking DBN variant of depth 3 using a neuromorphic event-based sensor (O’Connor, Neil, Liu, Delbruck, & Pfeiffer, 2013).”
Relational inductive biases, deep learning, and graph networks (2018, background): “…were developed in domains such as analogy-making, linguistic analysis, symbol manipulation, and other forms of relational reasoning (Smolensky, 1990; Hinton, 1990; Pollack, 1990; Elman, 1991; Plate, 1995; Eliasmith, 2013), as well as more integrative theories for how the mind works (Marcus, 2001).”
Toward an Integration of Deep Learning and Neuroscience (2016, background): “Some, such as vector symbolic architectures 53 , which were proposed in cognitive science (Plate, 1995; Stewart and Eliasmith, 2009; Eliasmith, 2013), are also being considered in the context of eﬃciently-trainable artiﬁcial neural networks (Danihelka et al., 2016)—in eﬀect, these systems learn how…”
Inferring brain-computational mechanisms with models of activity measurements (2016, background): “How these building blocks work together in biological brains to achieve intelligent adaptive behaviour, however, remains largely mysterious (Eliasmith 2013; Marblestone et al. 2016).”
Special Thematic Section on "Societal Change" A Complex Systems Approach to the Study of Ideology: Cognitive-Affective Structures and the Dynamics of Belief Systems (2013, background): “Recent advances in cognitive science such as the development of Eliasmith’s (2013) semantic pointer architecture of cognition might help us move beyond those limitations in the future.”
Working Memory and Attention – A Conceptual Analysis and Review (2019, unknown): “convolution of each content with its context (Eliasmith, 2013; Plate, 2003), so that they cannot be identified”
Nengo: a Python tool for building large-scale functional brain models (2014, methodology): “However, Nengo is unique in that it is built on a theoretical framework that has enabled a cognitive architecture (the Semantic Pointer Architecture) that maintains a high level of biological plausibility, and has been validated through the Spaun model and other past work.”
Biologically Plausible, Human-scale Knowledge Representation (2016, methodology): “For each experiment, a trial consists of using the network to answer a single question about the WordNet graph (the question is different for each experiment ).”
Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization (2019, background): “…networks that are unambiguously ‘connectionist’: trained recurrent nets do not rely on symbolic data and control structures such as trees and global variable binding, and can straightforwardly be implemented in biological networks (Eliasmith, 2013) or neuromorphic hardware (Merolla et al., 2014).”
Long short-term memory and Learning-to-learn in networks of spiking neurons (2018, result): “Relation to prior work: We refer to [13, 14, 15, 16] for summaries of preceding results on computational capabilities of RSNNs.”
Asking 'Why' in AI: Explainability of intelligent systems - perspectives and challenges (2018, background): “…question of to what extent cognitive modelling plays a useful role in explanation generation for deep learning-based AI systems is an interesting one, and is bound up with the discus-sionoftowhatextentsuchsystemsarebiologically-inspired(see Eliasmith (2015) for detailed discussion on this matter).”
The atoms of neural computation (2014, background): “Key sources influencing the overall breakdown include (Eliasmith, 2013; O’Reilly, 2006; Rajesh P.N. Rao, Olshausen, & Lewicki, 2002).”