Machine Learning Articles – Page 6

Michael Brenndoerfer

Machine Learning

Articles about traditional machine learning, optimization, bayesian methods, and other machine learning topics.

712 items · Page 6 of 15

Community

Learn with the community

Create a free account to keep your reading organized, join thoughtful discussions, and get more from every chapter.

Keep your place across books and articles
Ask questions and take part in discussions
Read with fewer interruptions

Join the community

Free to join · Takes less than a minute

Why

I created this space so readers can learn together, ask questions, and make sense of difficult ideas.

From readers1 / 12

Machine LearningLanguage AI Handbook

INT8 Quantization: Absmax

Jan 11, 2026·59 min read

Covers INT8 weight quantization with absmax and smooth quantization techniques. Solve the outlier problem in large language models.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

PII Removal: Detection, Redaction, and Privacy Preservation

Jan 10, 2026·53 min read

Detect and remove personal information from LLM training data with regex, named entity recognition, and hybrid privacy pipelines.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Toxicity Filtering: Classifiers, Thresholds

Jan 10, 2026·49 min read

Explains how toxicity classifiers work, how to calibrate thresholds for pretraining data.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Quality Filtering: Heuristics, Perplexity, and Classifiers

Jan 10, 2026·50 min read

Filter low-quality text from web corpora using heuristic rules, perplexity scoring, and classifier-based methods with tunable thresholds.

Open notebook

Language AI HandbookMachine LearningData, Analytics & AI

Weight Quantization Basics: Scale, Zero-Point & Calibration

Jan 10, 2026·59 min read

Explains how weight quantization maps floating-point values to integers, reducing LLM memory by 4x. Topics include scale, zero-point.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

MinHash: Jaccard Similarity, LSH, Near-Duplicate Detection

Jan 10, 2026·47 min read

Explains how MinHash compresses documents into compact signatures that estimate Jaccard similarity, enabling near-duplicate detection.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Language Identification: Models, Multilingual Handling

Jan 10, 2026·52 min read

Explains how language identification works in NLP pipelines. Topics include n-gram models, FastText LID, code-switching, confidence thresholds.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Hypothesis Testing: Test Selection and Reporting

Jan 10, 2026·18 min read

Practical reporting guidelines, summary of key concepts, test selection parameters table, multiple comparison corrections table.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Document Extraction with Trafilatura and HTML Parsing

Jan 9, 2026·55 min read

Extract clean text from HTML and PDFs for LLM training data. Topics include boilerplate removal, text density algorithms, Trafilatura.

Open notebook

Machine LearningLanguage AI HandbookSoftware EngineeringData, Analytics & AI

KV Cache Compression: Eviction, Quantization & H2O Algorithm

Jan 9, 2026·56 min read

Covers KV cache compression techniques including eviction strategies, attention sinks, the H2O algorithm, and INT8 quantization for efficient LLM inference.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Multiple Comparisons: FWER, FDR, Bonferroni, Holm

Jan 9, 2026·29 min read

Control false positives across multiple hypothesis tests with FWER, FDR, Bonferroni, Holm, and Benjamini-Hochberg procedures.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Web Crawling: Common Crawl, Robots.txt, and Freshness

Jan 8, 2026·52 min read

Explains how web crawlers discover and download internet content at scale, covering Common Crawl architecture, robots.txt compliance, politeness policies.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Evaluation Challenges: Contamination, Brittleness, Gaming

Jan 8, 2026·49 min read

Benchmark scores can mislead when test data leaks, metrics saturate, or systems game proxies. Covers contamination, brittleness, Goodhart's Law, and mitigation.

Open notebook

Machine LearningSoftware EngineeringLanguage AI Handbook

PagedAttention: Solving LLM KV Cache Memory Fragmentation

Jan 8, 2026·68 min read

Explains how PagedAttention uses virtual memory paging to eliminate KV cache fragmentation, enabling 5x better memory utilization in LLM serving systems.

Open notebook

Quantitative FinanceData, Analytics & AIMachine Learningalgorithmic-trading

Transaction Costs & Market Impact: Models & Analysis

Jan 8, 2026·56 min read

Covers transaction cost analysis and market impact modeling. Estimate spread, slippage, and liquidity to build realistic backtests and execution strategies.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Effect Sizes and Statistical Significance: Cohen's d

Jan 8, 2026·20 min read

Cohen's d measures effect size separately from statistical significance. Covers practical significance and why small p-values can describe small effects.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Benchmark Design: Construction, Annotation, Validity in NLP

Jan 7, 2026·56 min read

Build rigorous NLP benchmarks: task definition, dataset collection, annotation guidelines, inter-annotator agreement, contamination detection.

Open notebook

Language AI HandbookMachine LearningSoftware Engineering

KV Cache Memory for LLM Inference

Jan 7, 2026·52 min read

Calculate KV cache memory requirements for transformer models. Topics include batch size, context length, GQA optimization, and GPU deployment planning.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Sample Size, Minimum Detectable Effect & Power: Analysis

Jan 7, 2026·29 min read

Choose sample size and minimum detectable effect with power analysis. Covers underpowered studies, statistical sensitivity, and design tradeoffs.

Open notebook

Language AI HandbookMachine LearningData, Analytics & AI

KV Cache Explained: Efficient Attention for LLM Generation

Jan 6, 2026·56 min read

Explains how KV cache eliminates redundant attention computations in transformers. Topics include memory requirements, cache structure.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Type I and Type II Errors: False Positives, False Negatives

Jan 6, 2026·32 min read

Understanding false positives, false negatives, statistical power, and the tradeoff between error types. Balance Type I and Type II errors in study design.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Multimodal Applications: Documents, Medical, Video

Jan 5, 2026·61 min read

Explains how multimodal AI powers document understanding, medical imaging diagnostics, video analysis, and complex reasoning tasks across real-world domains.

Open notebook

Language AI HandbookMachine LearningData, Analytics & AI

Iterative Alignment: Online DPO & Self-Improvement Methods

Jan 5, 2026·48 min read

Covers iterative alignment for LLMs with online DPO, rolling references, Constitutional AI, and SPIN. Build self-improving models beyond single-shot training.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Image Generation: Diffusion Models, Text-to-Image, Editing

Jan 5, 2026·55 min read

Covers diffusion models from the DDPM objective to latent diffusion, classifier-free guidance, image editing techniques, ControlNet, and FID evaluation metrics.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

ANOVA (Analysis of Variance): One-Way ANOVA, Post-Hoc Tests

Jan 5, 2026·23 min read

One-way ANOVA, post-hoc tests, assumptions, and when to use ANOVA. Compare means across three or more groups while controlling Type I error rates.

Open notebook

Machine LearningLanguage AI HandbookData, Analytics & AI

RLAIF & Constitutional AI: Scalable Model Alignment

Jan 4, 2026·51 min read

Covers RLAIF and Constitutional AI for scalable model alignment. Use AI feedback, design constitutions, and train reward models effectively.

Open notebook

Quantitative FinanceMachine LearningData, Analytics & AI

Alternative Data and NLP in Quantitative Finance Strategies

Jan 4, 2026·56 min read

Extract trading signals from alternative data using NLP. Topics include sentiment analysis, text processing, and building news-based trading systems.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Image Understanding: VQA, Captioning and Visual Grounding

Jan 4, 2026·53 min read

Covers four core image understanding tasks: visual question answering, image captioning, visual grounding, and scene understanding.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Attention Analysis Limitations: When Weights Mislead

Jan 4, 2026·47 min read

Why attention weights fail as explanations, how manipulation studies expose their limits, and what gradient-based methods offer as more faithful alternatives.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

The F-Test and F-Distribution: Comparing Variances

Jan 4, 2026·24 min read

F-distribution, F-test for comparing variances, F-test in regression, and nested model comparison.

Open notebook

Data, Analytics & AIMachine LearningLanguage AI Handbook

Multimodal Foundations: Cross-Modal Alignment

Jan 3, 2026·50 min read

Multimodal models align text, images, and other inputs in shared embedding spaces. Covers contrastive loss, dual encoders, joint encoders, and tradeoffs.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Agent Safety: Alignment, Sandboxing, and Monitoring

Jan 3, 2026·55 min read

Build safe autonomous agents using action constraints, sandboxing, real-time monitoring, prompt injection defenses, and human-in-the-loop intervention patterns.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Multi-Agent Systems: Coordination and Communication

Jan 3, 2026·55 min read

Explains how multi-agent AI systems coordinate through topologies, communication protocols, role assignment.

Open notebook

Machine LearningLanguage AI Handbook

DPO Variants: IPO, KTO, ORPO & cDPO for LLM Alignment

Jan 3, 2026·65 min read

DPO variants include IPO, KTO, ORPO, and cDPO. Compare their objectives, data requirements, computational costs, and suitable alignment tasks.

Open notebook

Machine LearningQuantitative FinanceData, Analytics & AI

ML Trading Strategies: Signal Generation, Sentiment & RL

Jan 3, 2026·62 min read

Build ML-driven trading strategies covering return prediction, sentiment analysis, alternative data integration, and reinforcement learning for execution.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

The T-Test: One-Sample, Two-Sample (Pooled & Welch)

Jan 3, 2026·29 min read

Covers t-tests including one-sample, two-sample (pooled and Welch), paired tests, assumptions, and decision framework.

Open notebook

Language AI HandbookMachine LearningSoftware Engineering

DPO Implementation: PyTorch Training for LLM Alignment

Jan 2, 2026·56 min read

Implement Direct Preference Optimization in PyTorch. Topics include preference data formatting, loss computation, training loops.

Open notebook

Machine LearningQuantitative FinanceData, Analytics & AI

Machine Learning for Trading: Algorithms, Features

Jan 2, 2026·51 min read

Covers supervised ML algorithms for trading: linear models, random forests, gradient boosting.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Confidence Intervals and Test Assumptions

Jan 2, 2026·23 min read

Mathematical equivalence between confidence intervals and hypothesis tests, test assumptions (independence, normality, equal variances).

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

Z-Tests: One-Sample, Two-Sample and Proportion Tests

Jan 2, 2026·22 min read

Covers z-tests including one-sample, two-sample, and proportion tests. Topics include when to use z-tests, how to calculate test statistics.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningLanguage AI Handbook

Planning: Task Decomposition and Goal-Directed LLM Agents

Jan 1, 2026·61 min read

Explains how LLM agents plan, decompose tasks, execute multi-step goals, and recover from failures using architectures like ReWOO, Tree-of-Thought.

Open notebook

Language AI HandbookMachine Learning

DPO Derivation: From RLHF Objective to Direct Optimization

Jan 1, 2026·45 min read

Derive the DPO loss function from first principles. Explains how the optimal RLHF policy leads to reward reparameterization and direct preference optimization.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

P-values and Hypothesis Test Setup

Jan 1, 2026·21 min read

Foundation of hypothesis testing covering p-values, null and alternative hypotheses, one-sided vs two-sided tests.

Open notebook

Machine LearningLanguage AI Handbook

Direct Preference Optimization (DPO)

Dec 31, 2025·53 min read

Explains how DPO eliminates reward models from LLM alignment. Topics include the reward-policy duality that enables supervised preference learning.

Open notebook

Language AI HandbookMachine LearningSoftware Engineering

KL Divergence Penalty in RLHF: Theory & Implementation

Dec 30, 2025·69 min read

Explains how KL divergence prevents reward hacking in RLHF by keeping policies close to reference models.

Open notebook

Language AI HandbookMachine Learning

RLHF Pipeline: SFT, Reward Models, and PPO

Dec 29, 2025·61 min read

Covers RLHF pipeline with three stages: Supervised Fine-Tuning, Reward Model training, and PPO optimization. Topics include debugging techniques.

Open notebook

Language AI HandbookMachine LearningData, Analytics & AI

PPO for Language Models: Adapting RL to Text Generation

Dec 28, 2025·64 min read

Explains how PPO applies to language models. Topics include policy mapping, token action spaces, KL divergence penalties, and advantage estimation for RLHF.

Open notebook

Machine LearningLanguage AI Handbook