Nicole Sandra-Yaffa Dumont

Ms. Nicole Sandra-Yaffa Dumont

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2021 in Neural Computation
Verified
Journal Article
Open access
PDF file
AVAaron R. Voelker
Aaron R. Voelker
PBPeter Blouw
Peter Blouw
XCXuan Choo
Xuan Choo
NDNicole Sandra-Yaffa Dumont
Nicole Sandra-Yaffa Dumont
TSTerrence C Stewart
Terrence C Stewart
CEChris Eliasmith
Chris Eliasmith
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 fill these gaps, this work exploits a method for defining vector representations that bind discrete (symbol-like) entities to points in continuous topological spaces in order to simulate and predict the behavior of a range of dynamical systems. These vector representations are spatial semantic pointers (SSPs), and we demonstrate that they can (1) be used to model dynamical systems involving multiple objects represented in a symbol-like manner and (2) be integrated with deep neural networks to predict the future of physical trajectories. These results help unify what have traditionally appeared to be disparate approaches in machine learning.

31 January 2023 in Brain Sciences
Verified
Journal Article
Open access
PDF file
NDNicole Sandra-Yaffa Dumont
Nicole Sandra-Yaffa Dumont
ASAndreas Stöckel
Andreas Stöckel
PFP. Michael Furlong
P. Michael Furlong
MBMadeleine Bartlett
Madeleine Bartlett
CEChris Eliasmith
Chris Eliasmith
TSTerrence C Stewart
Terrence C Stewart
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, presenting them in a common framework. We expand on the NEF’s core principles of (a) specifying the desired tuning curves of neurons in different parts of the model, (b) defining the computational relationships between the values represented by the neurons in different parts of the model, and (c) finding the synaptic connection weights that will cause those computations and tuning curves. In particular, we show how to extend this to include complex spatiotemporal tuning curves, and then apply this approach to produce functional computational models of grid cells, time cells, path integration, sparse representations, probabilistic representations, and symbolic representations in the brain.

5 July 2023 in Frontiers in Neuroscience
Verified
Journal Article
Open access
NDNicole Sandra-Yaffa Dumont
Nicole Sandra-Yaffa Dumont
PFP. Michael Furlong
P. Michael Furlong
JOJeff Orchard
Jeff Orchard
CEChris Eliasmith
Chris Eliasmith
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-motion cues, sensory, and semantic information. Several specialized neuron classes have been identified in the mammalian brain as being involved in solving SLAM. While biology has inspired a whole class of SLAM algorithms, the use of semantic information has not been explored in such work. We present a novel, biologically plausible SLAM model called SSP-SLAM—a spiking neural network designed using tools for large scale cognitive modeling. Our model uses a vector representation of continuous spatial maps, which can be encoded via spiking neural activity and bound with other features (continuous and discrete) to create compressed structures containing semantic information from multiple domains (e.g., spatial, temporal, visual, conceptual). We demonstrate that the dynamics of these representations can be implemented with a hybrid oscillatory-interference and continuous attractor network of head direction cells. The estimated self-position from this network is used to learn an associative memory between semantically encoded landmarks and their positions, i.e., an environment map, which is used for loop closure. Our experiments demonstrate that environment maps can be learned accurately and their use greatly improves self-position estimation. Furthermore, grid cells, place cells, and object vector cells are observed by this model. We also run our path integrator network on the NengoLoihi neuromorphic emulator to demonstrate feasibility for a full neuromorphic implementation for energy efficient SLAM.

25 August 2021 in Computational Economics
Verified
Journal Article
Closed access
PDF file
TCThomas F. Coleman
Thomas F. Coleman
NDNicole Sandra-Yaffa Dumont
Nicole Sandra-Yaffa Dumont
WLWanqi Li
Wanqi Li
WLWenbin Liu
Wenbin Liu
ARAlexey Rubtsov
Alexey Rubtsov

17 September 2024
Verified
Book Chapter
Closed access
PDF file
PFP. Michael Furlong
P. Michael Furlong
KSKathryn Simone
Kathryn Simone
NDNicole Sandra-Yaffa Dumont
Nicole Sandra-Yaffa Dumont
MBMadeleine Bartlett
Madeleine Bartlett
TSTerrence C Stewart
Terrence C Stewart
CEChris Eliasmith
Chris Eliasmith

19 February 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
LVLaura Sainz Villalba
Laura Sainz Villalba
PFP. Michael Furlong
P. Michael Furlong
MBMadeleine Bartlett
Madeleine Bartlett
NDNicole Sandra-Yaffa Dumont
Nicole Sandra-Yaffa Dumont
The brain faces the feature binding problem: how are multiple stimulus features and variables combined into coherent representations that support flexible behavior? A key finding from neuroscience is that some brain regions employ factorized representations, where distinct features are encoded in neural state space in such a way that enables independent readout and robust generalization. Various algebraic operations have been proposed to model multi-variable representations, but despite extensive study of their theoretical properties (e.g., capacity, noise robustness), it remains unclear which operations produce the representational geometries observed in neural recordings. We systematically evaluate six binding operations implemented in recurrent spiking neural networks performing a working memory task. We find that only superposition and binding with slot-filler structure produce factorized geometry with favorable scaling, while the alternatives do not. These results provide a taxonomy linking algebraic binding operations to neural representational signatures, offering guidance for both computational modelers and experimentalists.