A survey of methods for low-power deep learning and computer vision
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the
most accurate DNNs require millions of parameters and operations, making them energy …
most accurate DNNs require millions of parameters and operations, making them energy …
Quantization and deployment of deep neural networks on microcontrollers
Embedding Artificial Intelligence onto low-power devices is a challenging task that has been
partly overcome with recent advances in machine learning and hardware design. Presently …
partly overcome with recent advances in machine learning and hardware design. Presently …
Autopruner: An end-to-end trainable filter pruning method for efficient deep model inference
Channel pruning is an important method to speed up CNN model's inference. Previous filter
pruning algorithms regard importance evaluation and model fine-tuning as two independent …
pruning algorithms regard importance evaluation and model fine-tuning as two independent …
Graph neural networks: Architectures, stability, and transferability
Graph neural networks (GNNs) are information processing architectures for signals
supported on graphs. They are presented here as generalizations of convolutional neural …
supported on graphs. They are presented here as generalizations of convolutional neural …
Rubiksnet: Learnable 3d-shift for efficient video action recognition
Video action recognition is a complex task dependent on modeling spatial and temporal
context. Standard approaches rely on 2D or 3D convolutions to process such context …
context. Standard approaches rely on 2D or 3D convolutions to process such context …
Deep geometric knowledge distillation with graphs
In most cases deep learning architectures are trained disregarding the amount of operations
and energy consumption. However, some applications, like embedded systems, can be …
and energy consumption. However, some applications, like embedded systems, can be …
Rethinking weight decay for efficient neural network pruning
Introduced in the late 1980s for generalization purposes, pruning has now become a staple
for compressing deep neural networks. Despite many innovations in recent decades …
for compressing deep neural networks. Despite many innovations in recent decades …
Complexity-Driven Model Compression for Resource-constrained Deep Learning on Edge
Recent advances in Artificial Intelligence (AI) on the Internet of Things (IoT) devices have
realized Edge AI in several applications by enabling low latency and energy efficiency …
realized Edge AI in several applications by enabling low latency and energy efficiency …
Complexity-driven cnn compression for resource-constrained edge ai
Recent advances in Artificial Intelligence (AI) on the Internet of Things (IoT)-enabled network
edge has realized edge intelligence in several applications such as smart agriculture, smart …
edge has realized edge intelligence in several applications such as smart agriculture, smart …
Towards a configurable and non-hierarchical search space for NAS
M Perrin, W Guicquero, B Paille, G Sicard - Neural Networks, 2024 - Elsevier
Abstract Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN)
design. However, current NAS methods generally use hard-coded search spaces, and …
design. However, current NAS methods generally use hard-coded search spaces, and …