Full-text search across 7055 articles. Combine with topic and date filters; results sorted by relevance.
A research implementation called PBTune applies Population-Based Training (PBT), an evolutionary algorithm from DeepMind, to automatically tune PostgreSQL database configurations without machine learning. The system main…
A new approach to test datasets for generalised machine learning tasks proposes drawing the test set from a distribution as different as possible from the training and validation sets, while still being in-distribution f…
The story of Clever Hans, a horse in early 1900s Germany who appeared to solve math problems but was actually responding to subtle cues from his trainer, continues to haunt AI research as a cautionary tale about unintend…
University of Minnesota researchers have developed an AI system that enables underwater robots to track diver stress levels by analyzing exhaled bubbles, a breakthrough that could improve safety for commercial and scient…
GoodWebTools, a set of privacy-first web tools that run entirely in the browser using WebAssembly, canvas, and on-device machine learning, has been launched at goodwebtools.com. The tools process files client-side so not…
A new tutorial video explains Maximum Likelihood Estimation (MLE) as the core engine behind most machine learning models, connecting it to KL divergence and information theory to demystify parameter estimation. The resou…
A new analysis identifies data and concept drift as the primary cause of machine learning model failures after deployment, warning that without rigorous MLOps strategies including automated monitoring and retraining, mod…
A Japanese firm plans to train a robot using AI to reproduce runners' movements, aiming to create a robotic running coach that can demonstrate proper form. The project, reported by Yomiuri Shimbun, seeks to leverage mach…
SHAP (SHapley Additive exPlanations) is the most effective tool for debugging machine learning models, particularly for detecting data leakage bugs where a feature contains target information unavailable at inference tim…
Japanese researchers at the University of Electro-Communications and confectionery maker Ginza Cozy Corner have developed AI-powered robots that replicate the hand movements of skilled confectioners, aiming to preserve t…
ArmanddeCacqueray released SquareNet, an open-source tool that transforms wild elephant images into flat grids for machine learning preparation, as shown in a demonstration GIF on GitHub.
A new analysis warns that AI-generated code for geographic information systems (GIS) can produce 'no errors' while being fundamentally wrong, citing coordinate reference system (CRS) mismatches, spatial autocorrelation i…
A developer has built Zamin, a scripting language with a Rust-based bytecode VM and GPU-accelerated machine learning. The language compiles to bytecode, features a register-based VM, and includes a mark-and-sweep garbage…
A submission described as 'blatant AI slop' won the $25,000 DeepMind Kaggle Grand Prize in the 'Measuring AGI' competition, sparking controversy over the quality and evaluation of AI-generated solutions in machine learni…
Philip Weiss released autoportrait, a JavaScript library that renders an image as a deterministic, reproducible painting timelapse on an HTML canvas, with no dependencies and no runtime machine learning. The tool compute…
A developer graded Helium's machine-learning-based option probability forecasts for AAPL contracts expiring June 2026 and found a mean Brier loss of 0.3846 on two predictions, worse than a coin flip. The project also rel…
A developer built BeatScope, a free offline audio analyzer for macOS/iPhone that detects musical key and tempo using a hand-rolled signal-processing pipeline. The tempo pipeline uses spectral flux onset detection, autoco…
A human must analyze and preprocess data before training a machine learning algorithm to maximize prediction accuracy. Key preparation activities include understanding data types, exploring data quality and inter-feature…
A developer built a neural network that can be trained using finger gestures, enabling intuitive, hands-on machine learning without a keyboard or mouse. The system uses a webcam to track finger movements and adjusts mode…
A study published in Science suggests that while AI has accelerated scientific discovery, it may also be narrowing the scope of research by focusing on problems that are easily solvable by machine learning, potentially r…