On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “NASNet”

Learning Transferable Architectures for Scalable Image Recognitioncs.CV

NASNet learns efficient image classification architectures.

problem Developing efficient neural network architectures for image recognition.

method Transfer learning of architectural building blocks from small to large datasets.

result NASNet achieves state-of-the-art accuracy on ImageNet and CIFAR-10.

transfer learning neural architecture search image classification CNN NASNet

2017-07-21abs ↗pdf ↗

Advanced Capsule Networks via Context Awarenesscs.LG

Improved Capsule Networks for better image restoration and context awareness.

problem Challenges in image context recognition for Capsule Networks.

method Expanding Pooling layers and increasing Reconstruction layers; comparing CNs with DL models on ASL dataset.

result Capsule Networks perform comparably to DL models but significantly reduce training time.

Capsule Networks Context Awareness Image Restoration Deep Learning ASL Dataset

2019-03-18abs ↗pdf ↗

Auto-Keras: An Efficient Neural Architecture Search Systemcs.LG

Auto-Keras efficiently searches neural architectures with less computation.

problem Expensive computational cost in existing NAS algorithms.

method Bayesian optimization guided by network morphism.

result Framework outperforms state-of-the-art methods on real-world datasets.

neural architecture search Bayesian optimization network morphism AutoML efficient computation

2018-06-27abs ↗pdf ↗

Efficient Neural Architecture Search via Parameter Sharingcs.LG

ENAS discovers efficient neural architectures quickly and cheaply.

problem Automatic model design and neural architecture search.

method Parameter sharing and policy gradient for subgraph selection.

result ENAS discovers novel architectures achieving state-of-the-art performance.

Neural Architecture Search Parameter Sharing Policy Gradient Efficient Model Design Automatic Machine Learning

2018-02-09abs ↗pdf ↗

Synaptic Strength For Convolutional Neural Networkcs.LG

Synaptic pruning reduces CNNs by 96% on CIFAR-10.

problem Memory and computation constraints in CNNs for mobile devices.

method Synaptic Pruning: data-driven method to prune connections based on Synaptic Strength.

result Significant size reduction and computation saving with up to 96% pruning on CIFAR-10.

CNNs Synaptic Pruning Mobile Devices Synaptic Strength Compression

2018-11-06abs ↗pdf ↗

Deep Learning Approaches with Explainable AI for Differentiating Alzheimer Disease and Mild Cognitive Impairmenteess.IV

Deep learning ensemble improves Alzheimer vs. Mild Cognitive Impairment diagnosis.

problem Differentiating Alzheimer Disease from Mild Cognitive Impairment.

method Hybrid deep learning ensemble framework using MRI slices, pretrained models, and stacked ensemble learning.

result State-of-the-art accuracy (99.21%) for Alzheimer vs. Mild Cognitive Impairment classification.

Alzheimer Disease Mild Cognitive Impairment Deep Learning MRI Ensemble Methods

2025-09-27abs ↗pdf ↗