Search Results for author:
Found 29 papers, 3 papers with code
Computing with Residue Numbers in High-Dimensional Representation
We introduce Residue Hyperdimensional Computing, a computing framework that unifies residue number systems with an algebra defined over random, high-dimensional vectors.
Efficient Decoding of Compositional Structure in Holistic Representations
In particular, we find that the decoding techniques from the sparse coding and compressed sensing literature (rarely used for Hyperdimensional Computing/Vector Symbolic Architectures) are also well-suited for decoding information from the compositional distributed representations.
Learning and generalization of compositional representations of visual scenes
In contrast to learning category labels, here we train deep neural networks to output the full compositional vector description of an input image.
Efficient Optimization with Higher-Order Ising Machines
A prominent approach to solving combinatorial optimization problems on parallel hardware is Ising machines, i. e., hardware implementations of networks of interacting binary spin variables.
Neuromorphic Visual Odometry with Resonator Networks
The VO network we propose generates and stores a working memory of the presented visual environment.
Neuromorphic Visual Scene Understanding with Resonator Networks
Understanding a visual scene by inferring identities and poses of its individual objects is still and open problem.
Cross-Frequency Coupling Increases Memory Capacity in Oscillatory Neural Networks
We show that for values of $Q$ which are the same as the ratio of $\gamma$ to $\theta$ oscillations observed in the hippocampus and the cortex, the associative memory achieves greater capacity and information storage than previous models.
Deep Learning in Spiking Phasor Neural Networks
Spiking Neural Networks (SNNs) have attracted the attention of the deep learning community for use in low-latency, low-power neuromorphic hardware, as well as models for understanding neuroscience.
Integer Factorization with Compositional Distributed Representations
In this paper, we present an approach to integer factorization using distributed representations formed with Vector Symbolic Architectures.
A probabilistic latent variable model for detecting structure in binary data
The model infers sparse activity in a set of binary latent variables, each describing the activity of a cell assembly.
Neural Manifold Clustering and Embedding
We argue that achieving manifold clustering with neural networks requires two essential ingredients: a domain-specific constraint that ensures the identification of the manifolds, and a learning algorithm for embedding each manifold to a linear subspace in the feature space.
Efficient Neuromorphic Signal Processing with Loihi 2
The biologically inspired spiking neurons used in neuromorphic computing are nonlinear filters with dynamic state variables -- very different from the stateless neuron models used in deep learning.
Computing on Functions Using Randomized Vector Representations
By analogy to VSA, we call this new function encoding and computing framework Vector Function Architecture (VFA).
Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware.
Perceptron Theory Can Predict the Accuracy of Neural Networks
The perceptron theory compares favorably to other methods that do not rely on training an estimator model.
Cellular Automata Can Reduce Memory Requirements of Collective-State Computing
The variable encoding uses a fixed set of random patterns, which has to be stored and kept available during the computation.
A Neural Network MCMC sampler that maximizes Proposal Entropy
However, in the continuous case, unfavorable geometry of the target distribution can greatly limit the efficiency of MCMC methods.
Variable Binding for Sparse Distributed Representations: Theory and Applications
One binding method for general sparse vectors extends earlier proposals to reduce the tensor product into a vector, such as circular convolution.
Resonator networks for factoring distributed representations of data structures
The ability to encode and manipulate data structures with distributed neural representations could qualitatively enhance the capabilities of traditional neural networks by supporting rule-based symbolic reasoning, a central property of cognition.
A Model for Image Segmentation in Retina
Networks with phase interactions set by standard representations of the feature graph (adjacency matrix, Graph Laplacian or modularity) failed to exhibit segmentation performance significantly over the baseline, a model of independent sensors.
Complex Amplitude-Phase Boltzmann Machines
We extend the framework of Boltzmann machines to a network of complex-valued neurons with variable amplitudes, referred to as Complex Amplitude-Phase Boltzmann machine (CAP-BM).
Neuromorphic Nearest-Neighbor Search Using Intel's Pohoiki Springs
Neuromorphic computing applies insights from neuroscience to uncover innovations in computing technology.
Learning Energy-Based Models in High-Dimensional Spaces with Multi-scale Denoising Score Matching
Recently, \citet{song2019generative} have shown that a generative model trained by denoising score matching accomplishes excellent sample synthesis, when trained with data samples corrupted with multiple levels of noise.
Annealed Denoising score matching: learning Energy based model in high-dimensional spaces
Energy based models outputs unmormalized log-probability values given datasamples.
Resonator Networks outperform optimization methods at solving high-dimensional vector factorization
We develop theoretical foundations of Resonator Networks, a new type of recurrent neural network introduced in Frady et al. (2020) to solve a high-dimensional vector factorization problem arising in Vector Symbolic Architectures.
Robust computation with rhythmic spike patterns
Here, we propose a novel type of attractor neural network in complex state space, and show how it can be leveraged to construct spiking neural networks with robust computational properties through a phase-to-timing mapping.
A theory of sequence indexing and working memory in recurrent neural networks
The theory describes linear readout of analog data, and readout with winner-take-all error correction of symbolic data as proposed in VSA models.
Theory of the superposition principle for randomized connectionist representations in neural networks
The superposition operations in different existing models are mapped to linear neural networks with unitary recurrent matrices, in which retrieval accuracy can be analyzed by a single equation.
Learning overcomplete, low coherence dictionaries with linear inference
Further, by comparing ICA algorithms on synthetic data and natural images to the computationally more expensive sparse coding solution, we show that the coherence control biases the exploration of the data manifold, sometimes yielding suboptimal solutions.
