Mastodawn

Tau leptons are electrons but heavier, but unlike electrons they are unstable and create many different detector signatures. So, #machinelearning This #CMSpaper describes how we use convolutional #neuralnets (that's ones that do image recognition!) to better see tau leptons arxiv.org/abs/2511.05468

Freya Blekman Mar 5

Freya Blekman Feb 23

Stephen Blum Feb 13

Softmax makes probabilities; softplus smoothly keeps outputs positive, not normalized.

#deeplearning #math #neuralnets

Paul Houle Jan 22

🧠 Human-like Working Memory from Artificial Intrinsic Plasticity Neurons

https://arxiv.org/abs/2512.15829

#ai #llm #research #cs #arxiv #neuralnets #memory

Human-like Working Memory from Artificial Intrinsic Plasticity Neurons

Working memory enables the brain to integrate transient information for rapid decision-making. Artificial networks typically replicate this via recurrent or parallel architectures, yet incur high energy costs and noise sensitivity. Here we report IPNet, a hardware-software co-designed neuromorphic architecture realizing human-like working memory via neuronal intrinsic plasticity. Exploiting Joule-heating dynamics of Magnetic Tunnel Junctions (MTJs), IPNet physically emulates biological memory volatility. The memory behavior of the proposed architecture shows similar trends in n-back, free recall and memory interference tasks to that of reported human subjects. Implemented exclusively with MTJ neurons, the architecture with human-like working memory achieves 99.65% accuracy on 11-class DVS gesture datasets and maintains 99.48% on a novel 22-class time-reversed benchmark, outperforming RNN, LSTM, and 2+1D CNN baselines sharing identical backbones. For autonomous driving (DDD-20), IPNet reduces steering prediction error by 14.4% compared to ResNet-LSTM. Architecturally, we identify a 'Memory-at-the-Frontier' effect where performance is maximized at the sensing interface, validating a bio-plausible near-sensor processing paradigm. Crucially, all results rely on raw parameters from fabricated devices without optimization. Hardware-in-the-loop validation confirms the system's physical realizability. Separately, energy analysis reveals a reduction in memory power of 2,874x compared to LSTMs and 90,920x versus parallel 3D-CNNs. This capacitor-free design enables a compact ~1.5um2 footprint (28 nm CMOS): a >20-fold reduction over standard LIF neurons. Ultimately, we demonstrate that instantiating human-like working memory via intrinsic neuronal plasticity endows neural networks with the dual biological advantages of superior dynamic vision processing and minimal metabolic cost.

arXiv.org

Paul Houle Dec 31

🤯 stable-pretraining-v1: Foundation Model Research Made Simple

https://arxiv.org/abs/2511.19484

#ai #llm #neuralnets #training #software #research #cs #foundationmodels

stable-pretraining-v1: Foundation Model Research Made Simple

Foundation models and self-supervised learning (SSL) have become central to modern AI, yet research in this area remains hindered by complex codebases, redundant re-implementations, and the heavy engineering burden of scaling experiments. We present stable-pretraining, a modular, extensible, and performance-optimized library built on top of PyTorch, Lightning, Hugging Face, and TorchMetrics. Unlike prior toolkits focused narrowly on reproducing state-of-the-art results, stable-pretraining is designed for flexibility and iteration speed: it unifies essential SSL utilities--including probes, collapse detection metrics, augmentation pipelines, and extensible evaluation routines--within a coherent and reliable framework. A central design principle is logging everything, enabling fine-grained visibility into training dynamics that makes debugging, monitoring, and reproducibility seamless. We validate the library by demonstrating its ability to generate new research insights with minimal overhead, including depthwise representation probing and the analysis of CLIP degradation under synthetic data finetuning. By lowering barriers to entry while remaining scalable to large experiments, stable-pretraining aims to accelerate discovery and expand the possibilities of foundation model research.

arXiv.org

Paul Houle Dec 5

📡 'Mind-captioning' technique can read human thoughts from brain scans

https://medicalxpress.com/news/2025-11-mind-captioning-technique-human-thoughts.html

#brain #neuroscience #neuralnets #mind #thoughts #telepathy

'Mind-captioning' technique can read human thoughts from brain scans

Reading brain activity with advanced technologies is not a new concept. However, most techniques have focused on identifying single words associated with an object or action a person is seeing or thinking of, or matching up brain signals that correspond to spoken words. Some methods used caption databases or deep neural networks, but these approaches were limited by database word coverage or introduced information not present in the brain. Generating detailed, structured descriptions of complex visual perceptions or thoughts remains difficult.

Medical Xpress

Paul Houle Nov 9

⚡ Team develops high-speed, ultra-low-power superconductive neuron device

https://techxplore.com/news/2025-10-team-high-ultra-power-superconductive.html

#electronics #neuralnets #hardware #superconductivity #engineering #research

Team develops high-speed, ultra-low-power superconductive neuron device

A research team has developed a neuron device that holds potential for application in large-scale, high-speed superconductive neural network circuits. The device operates at high speeds with ultra-low-power consumption and is tolerant to parameter fluctuations during circuit fabrication.

Tech Xplore