Tootfinder

A General Constructive Upper Bound on Shallow Neural Nets Complexity
Frantisek Hakl, Vit Fojtik
https://arxiv.org/abs/2510.06372 https://arxiv.org/pdf/2510…

A General Constructive Upper Bound on Shallow Neural Nets Complexity
We provide an upper bound on the number of neurons required in a shallow neural network to approximate a continuous function on a compact set with a given accuracy. This method, inspired by a specific proof of the Stone-Weierstrass theorem, is constructive and more general than previous bounds of this character, as it applies to any continuous function on any compact set.

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
Irene Tenison, Soumyajit Chatterjee, Fahim Kawsar, Mohammad Malekzadeh
https://arxiv.org/abs/2510.03101

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a target dataset can facilitate such adaptations; however, it remains impractical due to the increasing depth of modern neural nets, as well as the computational overhead associated with gradient-based optimization across all layers. Current approaches reduce trai…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/17]:
- Convolutional Neural Nets vs Vision Transformers: A SpaceNet Case Study with Balanced vs Imbalanc...
Akshar Gothi

Google DeepMind's mechanistic interpretability team details why it shifted from fully reverse-engineering neural nets to a focus on "pragmatic interpretability" (AI Alignment Forum)
https://www.alignmentforum.org/posts/StENzDcD3kpf…

Bayesian Topological Convolutional Neural Nets
Sarah Harkins Dayton, Hayden Everett, Ioannis Schizas, David L. Boothe Jr., Vasileios Maroulas
https://arxiv.org/abs/2510.11704 ht…

Bayesian Topological Convolutional Neural Nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important ma…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/5]:
- Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
Yuandong Tian

Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling
Junyi Yao, Parham Eftekhar, Gene Cheung, Xujin Chris Liu, Yao Wang, Wei Hu
https://arxiv.org/abs/2510.03027 …

Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling
Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph -- graph with no cycles of odd number of negative edges. A balanced signed graph has well-defined frequencies that map to…

It has occurred to me that a lot of data processing/transformation which is entirely feasible without highly trained LLMs and neural nets and GPUs is being handed over to such monstrosities in part because no one wants to do the app design. Like the current scourge of web-scraper bots, which seem to be doing #NLG with ultra-simple languages constructed by examining working URLs. It's a large project…

Replaced article(s) found for math.AC. https://arxiv.org/list/math.AC/new
[1/1]:
- Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
Yuandong Tian