A survey on hyperdimensional computing aka vector symbolic architectures, part ii: Applications, cognitive models, and challenges
This is Part II of the two-part comprehensive survey devoted to a computing framework most
commonly known under the names Hyperdimensional Computing and Vector Symbolic …
commonly known under the names Hyperdimensional Computing and Vector Symbolic …
Vector symbolic architectures as a computing framework for emerging hardware
This article reviews recent progress in the development of the computing framework vector
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …
A multi-scale fusion convolutional neural network based on attention mechanism for the visualization analysis of EEG signals decoding
D Li, J Xu, J Wang, X Fang, Y Ji - IEEE Transactions on Neural …, 2020 - ieeexplore.ieee.org
Brain-computer interface (BCI) based on motor imagery (MI) electroencephalogram (EEG)
decoding helps motor-disabled patients to communicate with external devices directly …
decoding helps motor-disabled patients to communicate with external devices directly …
How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition
A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general
understanding of the world. Such an agent would require the ability to continually …
understanding of the world. Such an agent would require the ability to continually …
Decomposing convolutional neural networks into reusable and replaceable modules
Training from scratch is the most common way to build a Convolutional Neural Network
(CNN) based model. What if we can build new CNN models by reusing parts from previously …
(CNN) based model. What if we can build new CNN models by reusing parts from previously …
A theoretical view on sparsely activated networks
Deep and wide neural networks successfully fit very complex functions today, but dense
models are starting to be prohibitively expensive for inference. To mitigate this, one …
models are starting to be prohibitively expensive for inference. To mitigate this, one …
Modularity in deep learning: A survey
H Sun, I Guyon - Science and Information Conference, 2023 - Springer
Modularity is a general principle present in many fields. It offers attractive advantages,
including, among others, ease of conceptualization, interpretability, scalability, module …
including, among others, ease of conceptualization, interpretability, scalability, module …
Decomposition of Deep Neural Networks into Modules via Mutation Analysis
A Ghanbari - Proceedings of the 33rd ACM SIGSOFT International …, 2024 - dl.acm.org
Recently, several approaches have been proposed for decomposing deep neural network
(DNN) classifiers into binary classifier modules to facilitate modular development and repair …
(DNN) classifiers into binary classifier modules to facilitate modular development and repair …
Discovering modular solutions that generalize compositionally
Many complex tasks and environments can be decomposed into simpler, independent parts.
Discovering such underlying compositional structure has the potential to expedite …
Discovering such underlying compositional structure has the potential to expedite …
Decomposing a recurrent neural network into modules for enabling reusability and replacement
Can we take a recurrent neural network (RNN) trained to translate between languages and
augment it to support a new natural language without retraining the model from scratch …
augment it to support a new natural language without retraining the model from scratch …