Foundations

ML Fundamentals

Neural networks, backpropagation, gradient descent — the maths behind AI

11,135
lessons
Skills in this topic
View full skill map →
ML Maths Basics
beginner
Manipulate vectors and matrices
Supervised Learning
beginner
Train decision trees, random forests, and neural nets
Unsupervised Learning
intermediate
Apply k-means and DBSCAN clustering
ML Pipelines
intermediate
Engineer features and handle missing data

Showing 547 reads from curated sources

ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation
arXiv:2604.01167v1 Announce Type: cross Abstract: Chest X-ray (CXR) segmentation is an important step in computer-aided diagnosis, yet deploying large foundatio
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
arXiv:2604.01216v1 Announce Type: cross Abstract: Reconstructing full spatio-temporal dynamics from sparse observations in both space and time remains a central
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Binned semiparametric Bayesian networks for efficient kernel density estimation
arXiv:2506.21997v3 Announce Type: replace-cross Abstract: This paper introduces a new type of probabilistic semiparametric model that takes advantage of data bi
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
arXiv:2510.00512v2 Announce Type: replace-cross Abstract: The transcriptional response to genetic perturbation reveals fundamental insights into complex cellula
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Seeing Beyond the Image: ECG and Anatomical Knowledge-Guided Myocardial Scar Segmentation from Late Gadolinium-Enhanced Images
arXiv:2511.14702v4 Announce Type: replace-cross Abstract: Accurate segmentation of myocardial scar from late gadolinium enhanced (LGE) cardiac MRI is essential
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning
arXiv:2603.09697v2 Announce Type: replace-cross Abstract: Recent advances in spectral optimization, notably Muon, have demonstrated that constraining update ste
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization
arXiv:2603.17219v2 Announce Type: replace-cross Abstract: Multi-site neuroimaging analysis is fundamentally confounded by scanner-induced covariate shifts, wher
7 Machine Learning Trends to Watch in 2026
Machine Learning Mastery 📐 ML Fundamentals ⚡ AI Lesson 2w ago
7 Machine Learning Trends to Watch in 2026
A couple of years ago, most machine learning systems sat quietly behind dashboards.
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
BenchScope: How Many Independent Signals Does Your Benchmark Provide?
arXiv:2603.29357v1 Announce Type: new Abstract: AI evaluation suites often report many scores without checking whether those scores carry independent informatio
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Rigorous Explanations for Tree Ensembles
arXiv:2603.29361v1 Announce Type: new Abstract: Tree ensembles (TEs) find a multitude of practical applications. They represent one of the most general and accu
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
A First Step Towards Even More Sparse Encodings of Probability Distributions
arXiv:2603.29691v1 Announce Type: new Abstract: Real world scenarios can be captured with lifted probability distributions. However, distributions are usually e
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
A Rational Account of Categorization Based on Information Theory
arXiv:2603.29895v1 Announce Type: new Abstract: We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules
arXiv:2603.29928v1 Announce Type: new Abstract: Tabular foundation models such as TabPFN and TabICL already produce full predictive distributions yet prevailing
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding
arXiv:2603.28780v1 Announce Type: cross Abstract: In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication co
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
A Multi-Modal Dataset for Ground Reaction Force Estimation Using Consumer Wearable Sensors
arXiv:2603.28784v1 Announce Type: cross Abstract: This Data Descriptor presents a fully open, multi-modal dataset for estimating vertical ground reaction force
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper 2w ago
WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression
arXiv:2603.28809v1 Announce Type: cross Abstract: Selecting appropriate values for the configurable parameters of Database Management Systems (DBMS) to improve
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Time is Not Compute: Scaling Laws for Wall-Clock Constrained Training on Consumer GPUs
arXiv:2603.28823v1 Announce Type: cross Abstract: Scaling laws relate model quality to compute budget (FLOPs), but practitioners face wall-clock time constraint
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
A Latent Risk-Aware Machine Learning Approach for Predicting Operational Success in Clinical Trials based on TrialsBank
arXiv:2603.29041v1 Announce Type: cross Abstract: Clinical trials are characterized by high costs, extended timelines, and substantial operational risk, yet rel
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication
arXiv:2603.29069v1 Announce Type: cross Abstract: Integer multiplication has long been considered a hard problem for neural networks, with the difficulty widely
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification
arXiv:2603.29449v1 Announce Type: cross Abstract: Minimizing invasive diagnostic procedures to reduce the risk of patient injury and infection is a central goal
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Training deep learning based dynamic MR image reconstruction using synthetic fractals
arXiv:2603.29922v1 Announce Type: cross Abstract: Purpose: To investigate whether synthetically generated fractal data can be used to train deep learning (DL) m
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Trimodal Deep Learning for Glioma Survival Prediction: A Feasibility Study Integrating Histopathology, Gene Expression, and MRI
arXiv:2603.29968v1 Announce Type: cross Abstract: Multimodal deep learning has improved prognostic accuracy for brain tumours by integrating histopathology and
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Quantifying Cross-Modal Interactions in Multimodal Glioma Survival Prediction via InterSHAP: Evidence for Additive Signal Integration
arXiv:2603.29977v1 Announce Type: cross Abstract: Multimodal deep learning for cancer prognosis is commonly assumed to benefit from synergistic cross-modal inte
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Generative Data Transformation: From Mixed to Unified Data
arXiv:2602.22743v2 Announce Type: replace Abstract: Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their traini
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Local Causal Discovery for Statistically Efficient Causal Inference
arXiv:2510.14582v2 Announce Type: replace-cross Abstract: Causal discovery methods can identify valid adjustment sets for causal effect estimation for a pair of
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Provably Extracting the Features from a General Superposition
arXiv:2512.15987v2 Announce Type: replace-cross Abstract: It is widely believed that complex machine learning models generally encode features through linear re
InfoQ AI/ML 📐 ML Fundamentals ⚡ AI Lesson 2w ago
Presentation: Hidden Decisions You Don’t Know You’re Making
Dan Fike and Shawna Martell explain how "hidden decisions" silently shape software architecture and engineering culture. By examining the invisible defaults beh
InfoQ AI/ML 📐 ML Fundamentals ⚡ AI Lesson 2w ago
Kubernetes Autoscaling Demands New Observability Focus Beyond Vendor Tooling
As adoption of Kubernetes autoscalers like Karpenter accelerates, a new set of platform-agnostic observability practices is emerging, shifting focus from tradit
From SQL Analytics to Predictive Decision Systems: Operationalizing ML Models in  Business Operation
Hackernoon 📐 ML Fundamentals ⚡ AI Lesson 2w ago
From SQL Analytics to Predictive Decision Systems: Operationalizing ML Models in Business Operation
SQL analytics shows what happened, but modern businesses need to act on what will happen next. The real challenge isn’t building ML models, it’s operationalizin
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Compliance-Aware Predictive Process Monitoring: A Neuro-Symbolic Approach
arXiv:2603.26948v1 Announce Type: new Abstract: Existing approaches for predictive process monitoring are sub-symbolic, meaning that they learn correlations bet
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper 2w ago
On the Relationship between Bayesian Networks and Probabilistic Structural Causal Models
arXiv:2603.27406v1 Announce Type: new Abstract: In this paper, the relationship between probabilistic graphical models, in particular Bayesian networks, and cau
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
A Multimodal Deep Learning Framework for Edema Classification Using HCT and Clinical Data
arXiv:2603.26726v1 Announce Type: cross Abstract: We propose AttentionMixer, a unified deep learning framework for multimodal detection of brain edema that comb
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion
arXiv:2603.26729v1 Announce Type: cross Abstract: The effective utilization of consistency is crucial for multi-view learning. GCNs leverage node connections to
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Ordinal Semantic Segmentation Applied to Medical and Odontological Images
arXiv:2603.26736v1 Announce Type: cross Abstract: Semantic segmentation consists of assigning a semantic label to each pixel according to predefined classes. Th
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
DSO: Dual-Scale Neural Operators for Stable Long-term Fluid Dynamics Forecasting
arXiv:2603.26800v1 Announce Type: cross Abstract: Long-term fluid dynamics forecasting is a critically important problem in science and engineering. While neura
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Dynamic resource matching in manufacturing using deep reinforcement learning
arXiv:2603.27066v1 Announce Type: cross Abstract: Matching plays an important role in the logical allocation of resources across a wide range of industries. The
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
RDEx-SOP: Exploitation-Biased Reconstructed Differential Evolution for Fixed-Budget Bound-Constrained Single-Objective Optimization
arXiv:2603.27089v1 Announce Type: cross Abstract: Bound-constrained single-objective numerical optimisation remains a key benchmark for assessing the robustness
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
RDEx-CSOP: Feasibility-Aware Reconstructed Differential Evolution with Adaptive epsilon-Constraint Ranking
arXiv:2603.27090v1 Announce Type: cross Abstract: Constrained single-objective numerical optimisation requires both feasibility maintenance and strong objective
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
RDEx-MOP: Indicator-Guided Reconstructed Differential Evolution for Fixed-Budget Multiobjective Optimization
arXiv:2603.27092v1 Announce Type: cross Abstract: Multiobjective optimisation in the CEC 2025 MOP track is evaluated not only by final IGD values but also by ho
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Bayes-MICE: A Bayesian Approach to Multiple Imputation for Time Series Data
arXiv:2603.27142v1 Announce Type: cross Abstract: Time-series analysis is often affected by missing data, a common problem across several fields, including heal
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Multimodal Forecasting for Commodity Prices Using Spectrogram-Based and Time Series Representations
arXiv:2603.27321v1 Announce Type: cross Abstract: Forecasting multivariate time series remains challenging due to complex cross-variable dependencies and the pr
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Diagnosing Non-Markovian Observations in Reinforcement Learning via Prediction-Based Violation Scoring
arXiv:2603.27389v1 Announce Type: cross Abstract: Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Multiple-Prediction-Powered Inference
arXiv:2603.27414v1 Announce Type: cross Abstract: Statistical estimation often involves tradeoffs between expensive, high-quality measurements and a variety of
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
arXiv:2603.27529v1 Announce Type: cross Abstract: Graph neural networks (GNNs) have achieved strong performance across various real-world domains. Nevertheless,
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
What-If Explanations Over Time: Counterfactuals for Time Series Classification
arXiv:2603.27792v1 Announce Type: cross Abstract: Counterfactual explanations emerge as a powerful approach in explainable AI, providing what-if scenarios that
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization
arXiv:2603.28040v1 Announce Type: cross Abstract: Deep learning training is non-deterministic: identical code with different random seeds produces models that a
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
TwinMixing: A Shuffle-Aware Feature Interaction Model for Multi-Task Segmentation
arXiv:2603.28233v1 Announce Type: cross Abstract: Accurate and efficient perception is essential for autonomous driving, where segmentation tasks such as drivab
ArXiv cs.AI 📐 ML Fundamentals 📄 Paper ⚡ AI Lesson 2w ago
MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations
arXiv:2603.28253v1 Announce Type: cross Abstract: Time series forecasting is vital across many domains, yet existing models struggle with fixed-length inputs an