Search Results for author:
Found 23 papers, 3 papers with code
Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks
We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content.
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.
Computing with Hypervectors for Efficient Speaker Identification
With only 1. 02k active parameters and a 128-minute pass through the training data we achieve Top-1 and Top-5 scores of 31% and 52% on the VoxCeleb1 dataset of 1, 251 speakers.
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.
Learning and Inference in Sparse Coding Models with Langevin Dynamics
Moreover we show that Langevin dynamics lead to an efficient procedure for sampling from the posterior distribution in the 'L0 sparse' regime, where latent variables are encouraged to be set to zero as opposed to having a small L1 norm.
Integer Factorization with Compositional Distributed Representations
In this paper, we present an approach to integer factorization using distributed representations formed with Vector Symbolic Architectures.
Computing on Functions Using Randomized Vector Representations
By analogy to VSA, we call this new function encoding and computing framework Vector Function Architecture (VFA).
Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing
Machine learning algorithms deployed on edge devices must meet certain resource constraints and efficiency requirements.
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.
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.
Word Embedding Visualization Via Dictionary Learning
Co-occurrence statistics based word embedding techniques have proved to be very useful in extracting the semantic and syntactic representation of words as low dimensional continuous vectors.
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.
The Sparse Manifold Transform
We present a signal representation framework called the sparse manifold transform that combines key ideas from sparse coding, manifold learning, and slow feature analysis.
DeepMovie: Using Optical Flow and Deep Neural Networks to Stylize Movies
The other naive method that initializes the optimization for the next frame using the rendered version of the previous frame also produces poor results because the features of the texture stay fixed relative to the frame of the movie instead of moving with objects in the scene.
Discovering Hidden Factors of Variation in DeepNetworks
Deep learning has enjoyed a great deal of success because of its ability to learnuseful features for tasks such as classification.
Discovering Hidden Factors of Variation in Deep Networks
Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification.
Group Sparse Coding with a Laplacian Scale Mixture Prior
We show that, due to the conjugacy of the Gamma prior, it is possible to derive efficient inference procedures for both the coefficients and the scale parameter.
An Unsupervised Algorithm For Learning Lie Group Transformations
Transformation operators are represented in their eigen-basis, reducing the computational complexity of parameter estimation to that of training a linear transformation model.
Learning transport operators for image manifolds
We describe a method for learning a group of continuous transformation operators to traverse smooth nonlinear manifolds.
Learning Horizontal Connections in a Sparse Coding Model of Natural Images
It has been shown that adapting a dictionary of basis functions to the statistics of natural images so as to maximize sparsity in the coefficients results in a set of dictionary elements whose spatial properties resemble those of V1 (primary visual cortex) receptive fields.
