Nearest Neighbour Search using binary neural networks

Ferro, Demetrio; Gripon, Vincent; Jiang, Xiaoran

doi:10.1109/ijcnn.2016.7727873

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If one wanted to build the most effective application possible, it could make sense to explore alternative approaches that tolerate less sparse data (Knoblauch, 2010(Knoblauch, , 2011(Knoblauch, , 2016. Besides the sparseness question, even the accuracy of the retrieval itself can be optimized through several previously explored techniques (Knoblauch, 2012(Knoblauch, , 2013Ferro, Gripon, & Jiang, 2016;Gripon, Lowe, & Vermet, 2018).…”

Section: Discussionmentioning

confidence: 99%

Storing Object-Dependent Sparse Codes in a Willshaw Associative Network

Sa-Couto

Wichert

2020

Neural Computation

View full text Add to dashboard Cite

Willshaw networks are single-layered neural networks that store associations between binary vectors. Using only binary weights, these networks can be implemented efficiently to store large numbers of patterns and allow for fault-tolerant recovery of those patterns from noisy cues. However, this is only the case when the involved codes are sparse and randomly generated. In this letter, we use a recently proposed approach that maps visual patterns into informative binary features. By doing so, we manage to transform MNIST handwritten digits into well-distributed codes that we then store in a Willshaw network in autoassociation. We perform experiments with both noisy and noiseless cues and verify a tenuous impact on the recovered pattern's relevant information. More specifically, we were able to perform retrieval after filling the memory to several factors of its number of units while preserving the information of the class to which the pattern belongs.

show abstract

Section: Discussionmentioning

confidence: 99%

Storing Object-Dependent Sparse Codes in a Willshaw Associative Network

Sa-Couto

Wichert

2020

Neural Computation

View full text Add to dashboard Cite

show abstract

“…Furthermore, the A-NNS solutions, especially based on locally sensitive hashing (Indyk and Motwani 1998;Har-Peled, Indyk, and Motwani 2012) have large space complexity, i.e., polynomial in size of dataset. We note that the A-NNS solutions are very much aligned to the vector (image) retrieval task (Jégou, Douze, and Schmid 2011;Yu et al 2015;Ferro, Gripon, and Jiang 2016) which need not have a neurally feasible retrieval algorithm.…”

Section: Introductionmentioning

confidence: 99%

Associative Memory Using Dictionary Learning and Expander Decoding

Mazumdar

Rawat

2017

AAAI

View full text Add to dashboard Cite

An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its noisy version. Designing an associative memory requires addressing two main tasks: 1) learning phase: given a dataset, learn a concise representation of the dataset in the form of a graphical model (or a neural network), 2) recall phase: given a noisy version of a message vector from the dataset, output the correct message vector via a neurally feasible algorithm over the network learnt during the learning phase. This paper studies the problem of designing a class of neural associative memories which learns a network representation for a large dataset that ensures correction against a large number of adversarial errors during the recall phase. Specifically, the associative memories designed in this paper can store dataset containing exp(n) n-length message vectors over a network with O(n) nodes and can tolerate Ω(n / polylog) adversarial errors. This paper carries out this memory design by mapping the learning phase and recall phase to the tasks of dictionary learning with a square dictionary and iterative error correction in an expander code, respectively.

show abstract

“…Furthermore, the A-NNS solutions, especially based on locally sensitive hashing [10,14] have large space complexity, i.e., polynomial in size of dataset. We note that the A-NNS solutions are very much aligned to the vector (image) retrieval task [7,17,33] which need not have a neurally feasible retrieval algorithm.…”

Section: Introductionmentioning

confidence: 99%

Associative Memory using Dictionary Learning and Expander Decoding

Mazumdar¹,

Rawat²

2016

Preprint

View full text Add to dashboard Cite

An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its noisy version. Designing an associative memory requires addressing two main tasks: 1) learning phase: given a dataset, learn a concise representation of the dataset in the form of a graphical model (or a neural network), 2) recall phase: given a noisy version of a message vector from the dataset, output the correct message vector via a neurally feasible algorithm over the network learnt during the learning phase. This paper studies the problem of designing a class of neural associative memories which learns a network representation for a large dataset that ensures correction against a large number of adversarial errors during the recall phase. Specifically, the associative memories designed in this paper can store dataset containing exp(n) n-length message vectors over a network with O(n) nodes and can tolerate Ω( n polylogn ) adversarial errors. This paper carries out this memory design by mapping the learning phase and recall phase to the tasks of dictionary learning with a square dictionary and iterative error correction in an expander code, respectively.

show abstract

Nearest Neighbour Search using binary neural networks

Cited by 6 publications

References 10 publications

Storing Object-Dependent Sparse Codes in a Willshaw Associative Network

Storing Object-Dependent Sparse Codes in a Willshaw Associative Network

Associative Memory Using Dictionary Learning and Expander Decoding

Associative Memory using Dictionary Learning and Expander Decoding

Contact Info

Product

Resources

About