Convolutional Neural Networks
PulseAugur coverage of Convolutional Neural Networks — every cluster mentioning Convolutional Neural Networks across labs, papers, and developer communities, ranked by signal.
-
New Mixture of Channel Experts layer slashes CNN computation
Researchers have introduced Mixture of Channel Experts (MoCE), a novel layer designed to replace standard pointwise projections in convolutional neural networks. Unlike traditional Mixture-of-Experts (MoE) models that s…
-
New Mixture of Channel Experts method boosts CNN efficiency
Researchers have developed a new method called Mixture of Channel Experts (MoCE) to improve the efficiency of convolutional neural networks. Unlike traditional Mixture-of-Experts models that route inputs through differe…
-
AI model-brain comparisons sensitive to image resolution, study finds
A new study published on arXiv investigates how the resolution at which convolutional neural networks are evaluated can significantly impact comparisons between different learning rules, particularly in the context of m…
-
Neural networks use computational graphs for training and medical image analysis
Neural networks utilize computational graphs for training, where operations are chained in a forward pass. The backward pass then calculates derivatives by applying the chain rule, multiplying local gradients at each no…
-
New theories explore how pre-training and sparse connectivity enhance deep learning generalization
Three new papers explore the theoretical underpinnings of generalization in deep learning. One paper identifies pre-training as a critical factor for weak-to-strong generalization, demonstrating its emergence through a …
-
DSLC club meetings cover deep learning interpretation and unsupervised learning
The Data Science Learning Community (DSLC) recently hosted two video sessions focused on machine learning concepts. One session, titled "Deep Learning with Python (3e): Interpreting what ConvNets learn," explored how co…
-
Quasi-Equivariant Metanetworks Advance Weight-Space Learning
Researchers have introduced quasi-equivariance as a novel concept for metanetworks, which are designed to operate on pretrained neural network weights. This new approach allows metanetworks to respect architectural symm…