Posts on machine learning, physics, and topology at irregularly spaced intervals.
# 1947 # Turing lecture First public lecture (London, 1947) to mention computer intelligence. Turing said: ‘What we want is a machine that can learn from experience… the possibility of letting t...
In the realm of amateur radio, the effective classification of signals and the mitigation of noise play crucial roles in ensuring reliable communication. Traditional methods for signal classification and noise reduction often rely on manual intervent...
Instance selection (or dataset reduction, or dataset condensation) is an important data pre-processing step that can be applied in many machine learning
We introduce milearn, a Python package for multi-instance learning (MIL) that follows the familiar scikit-learn fit/predict interface while providing a unified framework for both classical and neural-network-based MIL algorithms for regression and cl...
A database of opsin genotype-phenotype data and machine-learning models trained to predict opsin phenotypes. (⭐ 8)
Toy models, experiments and random notes on machine learning and deep learning. (⭐ 129)
Tools, scripts, toys, and utilities for Machine Box (⭐ 241)
Large language models (LLMs) are now being used with increasing frequency as chat bots, tasked with the summarizing information or generating text and code in accordance with user instructions. The rapid increase in reasoning capabilities and inferen...
See Google Translate's machine translation of 'responsable'. In other languages: French | Portuguese | Italian | German | Dutch | Swedish | Polish | Romanian | Czech | Greek | Turkish | Chinese | …
Can quantum computing protect AI from cyber attacks? Can we prevent malicious attacks and improve the cybersecurity of algorithms powered by artificial intelligence (AI)? Quantum machine learning may...
1 day ago · Maybe machine intelligence doesn’t require sentience, or autonomy, or curiosity, or feeling. Read: The alien intelligence in your pocket Say I concede all that.
Repertoire pour tous les codes du challenge 100 jours de machine learning #100JoursDeML (⭐ 80)
1 day ago · Maybe machine intelligence doesn’t require sentience, or autonomy, or curiosity, or feeling. Read: The alien intelligence in your pocket Say I concede all that.
Since my Voyager post was a hit, and someone contacted me to try an episode from Deep Space Nine "In the Pale Moonlight", I decided I would share a quick clip of the DS9 intro and a few seconds from t...
In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD requires a non-t...
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advances in machine learning involve larger neural networks with longer inf...
Big Data in IoT is a large and fast-developing area where many different methods and techniques can play a role. Due to rapid progress in Machine Learning and new hardware developments, a dynamic turnaround of methods and technologies can be observed...
Meshless methods are an active and modern branch of numerical analysis with many intriguing benefits. One of the main open research questions related to local meshless methods is how to select the best possible stencil - a collection of neighbouring...
A repository listing out the potential sources which will help you in preparing for a Data Science/Machine Learning interview. New resources added frequently. (⭐ 3310)