arXiv AI October 5, 2026 By Manfred M. Fischer, Joshua Pitts

The Effective Depth Paradox: Topology and Trainability in Deep CNNs

arXiv:2602. 13298v4 Announce Type: replace-cross Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topology and image classification performance across the architectural families VGG, ResNet, and GoogLeNet, evaluated on CIFAR-10 under a unified training protocol.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 30

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...

By Amirhossein Yousefiramandi

arXiv AI

Jun 26

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry

arXiv:2606. 26538v1 Announce Type: cross Abstract: Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value.

By Huzama Ahmad, Cao Viet Hai Nam, Se-Young Yun

llms efficiency

arXiv AI

Jul 1

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

arXiv:2505. 03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning benchmarks

arXiv AI

Jun 16

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

arXiv:2606. 16112v1 Announce Type: cross Abstract: Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth.

By Tom\'as Figliolia, Beren Millidge

llms efficiency

Hugging Face Trending Papers

Jun 22

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?

computer-vision benchmarks

arXiv AI

Jul 2

Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects

arXiv:2505. 03303v4 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning benchmarks

One email a morning, machine-written

Related stories

Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects