127 skills found · Page 5 of 5
farakiko / Xai4hepXAI toolbox for interpreting state-of-the-art ML algorithms for high energy physics.
shouryaverma / Interpretable Ml EcgDevelopment of Machine Learning Models to Detect Arrhythmia based on ECG Data - Interpretability
kitsumiko / Papers📚 A roadmap through AI/ML research literature. 200+ papers organized into a curriculum covering deep learning foundations, NLP, computer vision, interpretability, security, and emerging frontiers.
vishnupriyanpr / PrediChurnA full ML pipeline for customer churn prediction in telecom, banking, or SaaS. Includes robust data cleaning, automatic feature engineering, model training/tuning (Logistic Regression, RF, XGBoost), interpretability, and interactive dashboards for actionable business retention insights.
jphall663 / Jsm 2018 PaperPaper for 2018 Joint Statistical Meetings: https://ww2.amstat.org/meetings/jsm/2018/onlineprogram/AbstractDetails.cfm?abstractid=329539
interpretable-ml-class / Interpretable Ml Class.github.ioExplainable AI: From Simple Rules to Complex Generative Models
jesterhui / Interpretable Ml Description Chemisorption AlloysNo description available
ibrah5em / Ga Optimized TreesGA-Optimized Decision Trees: Evolve transparent ML models using multi-objective genetic algorithms. Perfect balance of accuracy and interpretability.
Cactus-proj / MicroML.jlA minimal ML, type-inferred, interpreted in 1000~ sloc.
KU-HJH / CoIBAThis repository contains the official code of the paper: "Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers", which is published in CVPR 2025.
Sonlux / AMRCAISAdaptive Multi-Regime Cross-Asset Intelligence System - A regime-first quantitative finance framework with 3-layer architecture (HMM/ML/Correlation/Volatility classifiers → 5 analytical modules → adaptive meta-learning) that interprets market signals dynamically across 4 economic regimes.
patr1ckzhu / HeartLens AppleWatchApple Watch ECG AI 深度分析 | 5 类心脏异常检测 + 心电波形染色可视化 + Qwen3.5 端侧解读 | 完全离线
CeciPani / MARLENAA python library to agnostically explain multi-label black-box classifiers (tabular data)
Kaushikjas10 / Liquefaction XGBoost SHAP Jas DodagoudarThis repository is associated with interpretable/explainable ML model for liquefaction potential assessment of soils. This model is developed using XGBoost and SHAP.
rootmos / Silly MlA a small ML-like language interpreted or compiled to x86-64 assembly with a custom runtime
parantapa / Integrated Directional GradientsImplementation of the Integrated Directional Gradients method for Deep Neural Network model explanations.
RAprogramm / Tsetlin RsHigh-performance Tsetlin Machine in Rust. Const generics, bitwise SIMD, zero-alloc inference. 25-92x faster clause evaluation.
andrewli77 / DISCThis repository contains an implementation of DISC, an algorithm for learning DFAs for multiclass sequence classification.
donlapark / XLabelXLabel: An Explainable Data Labeling Assistant
LeeGorden / Mental Disorder Diagnosis Multi BranchesAs applications of ML algorithms in real life become increasingly common, ethical issues of AI solutions emerge especially in a sensitive human-related field such as the medical care industry. To answer the need for ML models or methods with high interpretability in field of mental health, the responsible AI framework proposed innovatively integrates visualization algorithms t-SNE, convolution neural networks and explainable AI to evaluate predictions of mental disorders based on images generated and provide a corresponding explanation of why the Blackbox model makes such decisions. The output of the framework proposed are images demonstrated to be in both high accuracy and high interpretability in field experiments with accuracy higher than 90% by prediction based on bare human eyes. More importantly, the images generated under the responsible framework enable experts in the field of mental health to diagnose mental disorders even if they do not know ML algorithms.
