convolutional-neural-network

Tag

Cards List
#convolutional-neural-network

@HuggingModels: Ever wondered how AI can learn from video without needing humans to label every frame? Meet the ConvGRUAutoencoder, a m…

X AI KOLs Timeline · 2026-07-24 Cached

ConvGRUAutoencoder combines convolutional layers with gated recurrent units to compress and reconstruct video sequences, enabling unsupervised learning from video without human labeling.

0 favorites 0 likes
#convolutional-neural-network

Compact convolutional neural networks for AI-based drone detection system

arXiv cs.LG · 2026-07-21 Cached

This paper proposes lightweight convolutional neural networks for detecting FPV drones using time-domain rasterized RF signals, eliminating frequency-domain preprocessing and achieving high accuracy with low computational cost, suitable for embedded systems.

0 favorites 0 likes
#convolutional-neural-network

Image classification via a quantum-inspired strategy involving a mixture of experts

arXiv cs.LG · 2026-07-10 Cached

Proposes a quantum-inspired hybrid classical-quantum framework for image classification using a mixture of experts, demonstrating improved performance and reduced failure rate on MNIST and Fashion-MNIST datasets.

0 favorites 0 likes
#convolutional-neural-network

Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment

arXiv cs.LG · 2026-06-10 Cached

This paper introduces a learnable channel-class assignment mechanism for forward-only convolutional neural networks, combined with entropy and orthogonality regularization and a loss-aware layer contribution strategy. The method achieves state-of-the-art performance among forward-forward algorithms on CIFAR-10, CIFAR-100, and Tiny-ImageNet, significantly narrowing the gap with backpropagation.

0 favorites 0 likes
#convolutional-neural-network

Quantifying generalization in reinforcement learning

OpenAI Blog · 2018-12-06 Cached

OpenAI trained 9 agents on the CoinRun environment with varying numbers of training levels to quantify generalization in reinforcement learning, finding substantial overfitting even with 16,000 training levels and that IMPALA-CNN architectures generalize significantly better than Nature-CNN baselines.

0 favorites 0 likes
← Back to home

Submit Feedback