Chris Eliasmith

University of Waterloo | UWaterloo · Centre for Theoretical Neuroscience

Time is a central dimension against which perception, action, and cognition play out. From anticipating when future events will happen to recalling how long ago previous events occurred, humans and animals are exquisitely sensitive to temporal structure. Empirical evidence seems to suggest that estimating time prospectively (i.e., in passing) is qu...

The speed–accuracy trade-off (SAT) is the tendency for fast decisions to come at the expense of accurate performance. Evidence accumulation models such as the drift diffusion model can reproduce a variety of behavioral data related to the SAT, and their parameters have been linked to neural activities in the brain. However, our understanding of how...

The amygdala (AMY) is widely implicated in fear learning and fear behaviour, but it remains unclear how the many biological components present within AMY interact to achieve these abilities. Building on previous work, we hypothesize that individual AMY nuclei represent different quantities and that fear conditioning arises from error‐driven learnin...

Recent developments in generative models have demonstrated that with the right data set, techniques, computational infrastructure, and network architectures, it is possible to generate seemingly intelligent outputs, without explicitly reckoning with underlying cognitive processes. The ability to generate novel, plausible behaviour could be a boon t...

Distributed vector representations are a key bridging point between connectionist and symbolic representations in cognition. It is unclear how uncertainty should be modelled in systems using such representations. In this paper we discuss how bundles of symbols in certain Vector Symbolic Architectures (VSAs) can be understood as defining an object t...

To navigate in new environments, an animal must be able to keep track of its position while simultaneously creating and updating an internal map of features in the environment, a problem formulated as simultaneous localization and mapping (SLAM) in the field of robotics. This requires integrating information from different domains, including self-m...

Time is a central dimension against which perception, action, and cognition play out. From anticipating when future events will happen to recalling how long ago previous events occurred, humans and animals are exquisitely sensitive to temporal structure. Empirical evidence seems to suggest that estimating time prospectively (i.e., in passing) is qu...

In this paper, we present a fully spiking neural network running on Intel’s Loihi chip for operational space control of a simulated 7-DOF arm. Our approach uniquely combines neural engineering and deep learning methods to successfully implement position and orientation control of the end effector. The development process involved 4 stages: 1) Desig...

As neuromorphic hardware begins to emerge as a viable target platform for artificial intelligence (AI) applications, there is a need for tools and software that can effectively compile a variety of AI models onto such hardware. Nengo (http://nengo.ai) is an ecosystem of software designed to fill this need with a suite of tools for creating, trainin...

The Neural Engineering Framework (Eliasmith & Anderson, 2003) is a long-standing method for implementing high-level algorithms constrained by low-level neurobiological details. In recent years, this method has been expanded to incorporate more biological details and applied to new tasks. This paper brings together these ongoing research strands, pr...

Abstract—Unmanned aerial vehicles (UAVs) need more au- tonomy. In light of inherent size, weight and power (SWaP) constraints, avionics with artificial intelligence implemented using neuromorphic technology offers a potential solution. We demon- strate intelligent drone control using spiking neural networks (SNNs), which can run on neuromorphic har...

Improving biological plausibility and functional capacity are two important goals for brain models that connect low-level neural details to high-level behavioral phenomena. We develop a method called “oracle-supervised Neural Engineering Framework” (osNEF) to train biologically-detailed spiking neural networks that realize a variety of cognitively-...

In this report we consider the following problem: Given a trained model that is partially faulty, can we correct its behaviour without having to train the model from scratch? In other words, can we ``debug" neural networks similar to how we address bugs in our mathematical models and standard computer code. We base our approach on the hypothesis th...

Mixed-signal neuromorphic computers often emulate some variant of the LIF neuron model. While, in theory, two-layer networks of these neurons are universal function approximators, single-layer networks consisting of slightly more complex neurons can, at the cost of universality, be more efficient. In this paper, we discuss a family of LIF neurons w...

Mutual information (MI) is a standard objective function for driving exploration. The use of Gaussian processes to compute information gain is limited by time and memory complexity that grows with the number of observations collected.We present an efficient implementation of MI-driven exploration by combining vector symbolic architectures with Baye...

Recent studies have demonstrated that the performance of transformers on the task of language modeling obeys a power-law relationship with model size over six orders of magnitude. While transformers exhibit impressive scaling, their performance hinges on processing large amounts of data, and their computational and memory requirements grow quadrati...

We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword spotting and adaptive robotic control. Keyword spotting is commonly used in smart speakers to listen for wake words, and adaptive control is used in robotic applications to adapt to unknown dynami...

While neural networks are highly effective at learning task-relevant representations from data, they typically do not learn representations with the kind of symbolic structure that is hypothesized to support high-level cognitive processes, nor do they naturally model such structures within problem domains that are continuous in space and time. To f...

We seek to investigate the scalability of neuromorphic computing for computer vision, with the objective of replicating non-neuromorphic performance on computer vision tasks while reducing power consumption. We convert the deep Artificial Neural Network (ANN) architecture U-Net to a Spiking Neural Network (SNN) architecture using the Nengo framewor...

Neurophysiology and neuroanatomy constrain the set of possible computations that can be performed in a brain circuit. While detailed data on brain microcircuits is sometimes available, cognitive modelers are seldom in a position to take these constraints into account. One reason for this is the intrinsic complexity of accounting for biological mech...

Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant (LTI) memory component of the LMU to construct a simplified variant that can be parallelized during training (and yet executed as...

Nonlinear interactions in the dendritic tree play a key role in neural computation. Nevertheless, modeling frameworks aimed at the construction of large-scale, functional spiking neural networks, such as the Neural Engineering Framework, tend to assume a linear superposition of postsynaptic currents. In this letter, we present a series of extension...

Decision making (DM) requires the coordination of anatomically and functionally distinc cortical and subcortical areas. While previous computational models have studied these subsystems in isolation, few models explore how DM holistically arises from their interaction. We propose a spiking neuron model that unifies various components of DM, then sh...

In this paper we demonstrate how the Nengo neural modeling and simulation libraries enable users to quickly develop robotic perception and action neural networks for simulation on neuromorphic hardware using tools they are already familiar with, such as Keras and Python. We identify four primary challenges in building robust, embedded neurorobotic...

We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword spotting and adaptive robotic control. Keyword spotting is commonly used in smart speakers to listen for wake words, and adaptive control is used in robotic applications to adapt to unknown dynami...

Keyword spotting (KWS) provides a critical user interface for many mobile and edge applications, including phones, wearables, and cars. As KWS systems are typically 'always on', maximizing both accuracy and power efficiency are central to their utility. In this work we use hardware aware training (HAT) to build new KWS neural networks based on the...

We present the context-unified encoding (CUE) model, a large-scale spiking neural network model of human memory. It combines and integrates activity-based short-term memory (STM) with weight-based long-term memory. The implementation with spiking neurons ensures biological plausibility and allows for predictions on the neural level. At the same tim...

In this paper we demonstrate how the Nengo neural modeling and simulation libraries enable users to quickly develop robotic perception and action neural networks for simulation on neuromorphic hardware using familiar tools, such as Keras and Python. We identify four primary challenges in building robust, embedded neurorobotic systems: 1) developing...

The machine learning community has become increasingly interested in the energy efficiency of neural networks. The Spiking Neural Network (SNN) is a promising approach to energy-efficient computing, since its activation levels are quantized into temporally sparse, one-bit values (i.e., "spike" events), which additionally converts the sum over weigh...

We propose a novel memory cell for recurrent neural networks that dynamically maintains information across long windows of time using relatively few resources. The Legendre Memory Unit (LMU) is mathematically derived to orthogonalize its continuous-time history-doing so by solving d coupled ordinary differential equations (ODEs), whose phase space...

Most computational models of timing rely on well-defined start- and stop-signals, however, these are quite rare in our natural environments. Moreover, theories typically propose different mechanisms to account for retrospective and prospective timing, an assumption that is difficult to align with naturalistic, continuative types of timing. Here we...

Predicting future motion of other vehicles or, more generally, the development of traffic situations, is an essential step towards secure, context-aware automated driving. On the one hand, human drivers are able to anticipate driving situations continuously based on the currently perceived behavior of other traffic participants while incorporating...

We propose a cognitively plausible method for representing and querying spatial relationships in a neural architecture. This technique employs a fractional binding operator that captures continuous spatial information in spatial semantic pointers (SSPs). We propose a model that takes an image with several objects, parses the image into an SSP memor...

We present a novel method for constructing neurally implemented spatial representations that we show to be useful for building models of spatial cognition. This method represents continuous (i.e., real-valued) spaces using neurons, and identifies a set of operations for manipulating these representations. Specifically, we use "fractional binding" t...

We propose a spiking recurrent neural network model of flexible human timing behavior based on the delay network. The well-known 'scalar property' of timing behavior arises from the model in a natural way, and critically depends on how many dimensions are used to represent the history of stimuli. The model also produces heterogeneous firing pattern...

Hyperopt-sklearn is a software project that provides automated algorithm configuration of the Scikit-learn machine learning library. Following Auto-Weka, we take the view that the choice of classifier and even the choice of preprocessing module can be taken together to represent a single large hyperparameter optimization problem. We use Hyperopt to...

Nonlinear interactions in the dendritic tree play a key role in neural computation. Nevertheless, modeling frameworks aimed at the construction of large-scale, functional spiking neural networks tend to assume linear, current-based superposition of post-synaptic currents. We extend the theory underlying the Neural Engineering Framework to systemati...

Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter running on more conventional hardwa...

We present a new binding operation, vector-derived transformation binding (VTB), for use in vector symbolic architectures (VSA). The performance of VTB is compared to circular convolution, used in holographic reduced representations (HRRs), in terms of list and stack encoding capacity. A special focus is given to the possibility of a neural impleme...

Braindrop is the first neuromorphic system designed to be programmed at a high level of abstraction. Previous neuromorphic systems were programmed at the neurosynaptic level and required expert knowledge of the hardware to use. In stark contrast, Braindrop’s computations are specified as coupled nonlinear dynamical systems and synthesized to the ha...

Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter running on more conventional hardwa...

The representation of semantic knowledge poses a central modelling decision in many models of cognitive phenomena. However, not all such representations reflect properties observed in human semantic networks. Here, we evaluate the psychological plausibility of two distributional semantic models widely used in natural language processing: word2vec a...

Background: Parkinson's disease affects many motor processes including speech. Besides drug treatment, deep brain stimulation (DBS) in the subthalamic nucleus (STN) and globus pallidus internus (GPi) has developed as an effective therapy. Goal: We present a neural model that simulates a syllable repetition task and evaluate its performance when var...

Researchers building spiking neural networks face the challenge of improving the biological plausibility of their model networks while maintaining the ability to quantitatively characterize network behavior. In this work, we extend the theory behind the neural engineering framework (NEF), a method of building spiking dynamical networks, to permit t...

Neural networks have long been used to study linguistic phenomena spanning the domains of phonology, morphology, syntax, and semantics. Of these domains, semantics is somewhat unique in that there is little clarity concerning what a model needs to be able to do in order to provide an account of how the meanings of complex linguistic expressions, su...

I argue that a theory of category meaning that starts with the shared resources of all animals (i.e., neurons) can, if suitably constructed, provide solutions to traditional problems in semantics. I argue that traditional approaches that rely too heavily on linguistics or folk psychological categories are likely to lead us astray. In light of these...

The mathematical model underlying the Neural Engineering Framework (NEF) expresses neuronal input as a linear combination of synaptic currents. However, in biology, synapses are not perfect current sources and are thus nonlinear. Detailed synapse models are based on channel conductances instead of currents, which require independent handling of exc...

Prescribed Error Sensitivity (PES) is a biologically plausible supervised learning rule that is frequently used with the Neural Engineering Framework (NEF). PES modifies the connection weights between populations of spiking neurons to minimize an error signal. Continuing the work of Voelker (2015), we solve for the dynamics of PES, while filtering...

We review our current software tools and theoretical methods for applying the Neural Engineering Framework to state-of-the-art neuromorphic hardware. These methods can be used to implement linear and nonlinear dynamical systems that exploit axonal transmission time-delays, and to fully account for nonideal mixed-analog-digital synapses that exhibit...

In this paper, we present a spiking neural model of life span inference. Through this model, we explore the biological plausibility of performing Bayesian computations in the brain. Specifically, we address the issue of representing probability distributions using neural circuits and combining them in meaningful ways to perform inference. We show t...

Winner-take-all (WTA) mechanisms are an important component of many cognitive models. For example, they are often used to decide between multiple choices or to selectively direct attention. Here we compare two biologically plausible, spiking neural WTA mechanisms. We first provide a novel spiking implementation of the well-known leaky, competing ac...

We develop a novel, biologically detailed neural model of reinforcement learning (RL) processes in the brain. This model incorporates a broad range of biological features that pose challenges to neural RL, such as temporally extended action sequences, continuous environments involving unknown time delays, and noisy/imprecise computations. Most sign...

The Neural Engineering Framework (NEF) is a theory for mapping computations onto biologically plausible networks of spiking neurons. This theory has been applied to a number of neuromorphic chips. However, within both silicon and real biological systems, synapses exhibit higher-order dynamics and heterogeneity. To date, the NEF has not explicitly a...

One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that...

Generating associations is important for cognitive tasks including language acquisition and creative problem solving. It remains an open question how the brain represents and processes associations. The Remote Associates Test (RAT) is a task, originally used in creativity research, that is heavily dependent on generating associations in a search fo...

We use a spiking neural network model of working memory (WM) capable of performing the spatial delayed response task (DRT) to investigate two drugs that affect WM: guanfacine (GFC) and phenylephrine (PHE). In this model, the loss of information over time results from changes in the spiking neural activity through recurrent connections. We reproduce...

The ability to improve in speed and accuracy as a result of repeating some task is an important hallmark of intelligent biological systems. Although gradual behavioral improvements from practice have been modeled in spiking neural networks, few such models have attempted to explain cognitive development of a task as complex as addition. In this wor...

We present a spiking neuron model of the motor cortices and cerebellum of the motor control system. The model consists of anatomically organized spiking neurons encompassing premotor, primary motor, and cerebellar cortices. The model proposes novel neural computations within these areas to control a nonlinear three-link arm model that can adapt to...

The ability to associate words is an important cognitive skill. In this study we investigate different methods for representing word associations in the brain, using the Remote Associates Test (RAT) as a task. We explore representations derived from free association norms and statistical n-gram data. Although n-gram representations yield better per...

Models of neural systems often use idealized inputs and outputs, but there is also much to learn by forcing a neural model to interact with a complex simulated or physical environment. Unfortunately, sophisticated interactions require models of large neural systems, which are difficult to run in real time. We have prototyped a system that can simul...

Past research on action planning has shed light on the neural mechanisms underlying the selection of simple motor actions, along with the cognitive mechanisms underlying the planning of action sequences in constrained problem solving domains. We extend this research by describing a neural model that rapidly plans action sequences in relatively unco...

The ability to improve in speed and accuracy as a result of repeating some task is an important hallmark of intelligent biological systems. We model the progression from a counting-based strategy for addition to a recall-based strategy. The model consists of two networks working in parallel: a slower basal ganglia loop, and a faster cortical networ...

In this paper, we present a spiking neural model of context dependent decision making. Prefrontal cortex (PFC) plays a fundamental role in context dependent behaviour. We model the PFC at the level of single spiking neurons, to explore the underlying computations which determine its contextual responses. The model is built using the Neural Engineer...

The biological brain is a highly plastic system within which the efficacy and structure of synaptic connections are constantly changing in response to internal and external stimuli. While numerous models of this plastic behavior exist at various levels of abstraction, how these mechanisms allow the brain to learn meaningful values is unclear. The N...

Production and comprehension of speech are closely interwoven. For example, the ability to detect an error in one's own speech, halt speech production, and finally correct the error can be explained by assuming an inner speech loop which continuously compares the word representations induced by production to those induced by perception at various c...

Large-scale neural models are needed in order to understand the biological underpinnings of complex cognitive behavior. Good methods for constructing such models should provide for: first, abstraction (analysis across levels of description); second, integration (incorporation of simpler models to build more complex ones); third, empirical contact (...