Machine Learning Articles – Page 10

Michael Brenndoerfer

Machine Learning

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

712 items · Page 10 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

Data, Analytics & AIMachine LearningLanguage AI Handbook

In-Context Learning Without Fine-Tuning

Jul 25, 2025·51 min read

Explains how large language models learn new tasks from prompt demonstrations without weight updates.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningHistory of Language AI

InstructGPT and RLHF: Aligning LLMs with Human Preferences

Jul 25, 2025·16 min read

Covers OpenAI's InstructGPT research from 2022, including the three-stage RLHF training process, supervised fine-tuning, reward modeling.

Open notebook

AI Agent HandbookMachine LearningData, Analytics & AISoftware Engineering

Agents Working Together: Multi-Agent Systems

Jul 25, 2025·17 min read

Explains how multiple AI agents collaborate through specialization, parallel processing, and coordination.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

Decoding Temperature

Jul 24, 2025·55 min read

Explains how temperature scaling reshapes probability distributions during text generation, with mathematical foundations, implementation details.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

UMAP: Uniform Manifold Approximation and Projection

Jul 24, 2025·40 min read

Covers UMAP dimensionality reduction, including mathematical foundations, fuzzy simplicial sets, manifold learning.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

ELECTRA: Efficient Pre-training

Jul 23, 2025·42 min read

Explains how ELECTRA achieves BERT-level performance with 1/4 the compute by detecting replaced tokens instead of predicting masked ones.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningHistory of Language AI

The Pile: Open-Source Training Dataset for LLMs

Jul 23, 2025·14 min read

Covers EleutherAI's The Pile, the early 825GB open-source dataset that broadened access to high-quality training data for large language models.

Open notebook

AI Agent HandbookMachine LearningSoftware Engineering

AI Agent Planning: Meeting Scheduling and Summaries

Jul 23, 2025·10 min read

See how AI agents use planning to handle complex, multi-step tasks. Topics include task decomposition, sequential execution.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

GPT-2: Scaling Language Models for Zero-Shot Learning

Jul 22, 2025·52 min read

Examines GPT-2's architecture, model sizes, WebText training, and zero-shot capabilities that changed language modeling through scale.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

BERT Fine-tuning: Classification, NER & Question Answering

Jul 21, 2025·44 min read

Covers BERT fine-tuning for downstream NLP tasks. Topics include task-specific heads, hyperparameter tuning, and strategies to prevent catastrophic forgetting.

Open notebook

Data, Analytics & AIMachine LearningMachine Learning from Scratch

PCA (Principal Component Analysis): Math & Implementation

Jul 21, 2025·23 min read

Covers Principal Component Analysis, including mathematical foundations, eigenvalue decomposition.

Open notebook

History of Language AIMachine LearningData, Analytics & AILLM and GenAI

Dense Passage Retrieval and Retrieval-Augmented Generation

Jul 21, 2025·18 min read

Covers Dense Passage Retrieval (DPR) and Retrieval-Augmented Generation (RAG), the 2020 innovations.

Open notebook

AI Agent HandbookMachine LearningSoftware Engineering

Plan and Execute: Turning Agent Plans into Action

Jul 21, 2025·12 min read

Explains how AI agents execute multi-step plans sequentially, handle failures gracefully, and adapt when things go wrong.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

GPT-1: Generative Pretraining for Language Understanding

Jul 20, 2025·68 min read

GPT-1 paired generative pretraining with task-specific fine-tuning. Covers its architecture, objective, benchmark results, and role in transfer learning.

Open notebook

Data, Analytics & AISoftware EngineeringMachine Learning

Simulating stock market returns using Monte Carlo

Jul 19, 2025·13 min read

Use Monte Carlo simulation to model and analyze stock market returns, estimate future performance.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

GPT-3: Scale, Few-Shot and In-Context Learning

Jul 19, 2025·93 min read

Examines GPT-3's 175B parameter architecture, the emergence of few-shot learning, in-context learning mechanisms.

Open notebook

History of Language AIMachine LearningData, Analytics & AI

BLOOM: Open-Access Multilingual Language Model

Jul 19, 2025·6 min read

Covers BLOOM, the BigScience collaboration's 176-billion-parameter open-access multilingual language model released in 2022.

Open notebook

AI Agent HandbookMachine LearningData, Analytics & AISoftware Engineering

Task Decomposition for AI Agents

Jul 19, 2025·13 min read

Explains how AI agents break down complex goals into manageable subtasks. Topics include task decomposition strategies, sequential vs parallel tasks.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

DeBERTa: Disentangled Attention and Enhanced Mask Decoding

Jul 18, 2025·61 min read

Covers DeBERTa's disentangled attention mechanism that separates content and position representations.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningMachine Learning from Scratch

XGBoost: Extreme Gradient Boosting

Jul 18, 2025·78 min read

Covers XGBoost (eXtreme Gradient Boosting), including second-order Taylor expansion, regularization techniques, split gain optimization, ranking loss functions.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

BERT Pre-training: MLM, NSP & Training Strategies Explained

Jul 17, 2025·42 min read

Covers BERT pre-training covering masked language modeling, next sentence prediction, data preparation, hyperparameters.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningHistory of Language AI

Scaling Laws for Neural LLMs

Jul 17, 2025·20 min read

Covers the 2020 scaling laws discovered by Kaplan et al. Explains how power-law relationships predict model performance from scale.

Open notebook

AI Agent HandbookMachine LearningSoftware Engineering

Environment Boundaries and Constraints

Jul 17, 2025·18 min read

Define what your AI agent can and cannot do through access controls, action policies, rate limits, and scope boundaries.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

ALBERT: Parameter-Efficient BERT with Factorized Embeddings

Jul 16, 2025·42 min read

Explains how ALBERT reduces BERT's size by 18x using factorized embeddings and cross-layer parameter sharing while maintaining competitive performance.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

RoBERTa: Robustly Optimized BERT Pretraining Approach

Jul 15, 2025·55 min read

Explains how RoBERTa surpassed BERT using the same architecture by removing Next Sentence Prediction, implementing dynamic masking.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningMachine Learning from Scratch

SHAP (SHapley Additive exPlanations): Model Interpretability

Jul 15, 2025·55 min read

Covers SHAP values covering mathematical foundations, feature attribution, and practical implementations for explaining any machine learning model.

Open notebook

History of Language AIMachine LearningData, Analytics & AI

Chinchilla Scaling Laws: Compute-Optimal Training

Jul 15, 2025·18 min read

Covers the Chinchilla scaling laws introduced in 2022. Explains how compute-optimal training balances model size and training data.

Open notebook

AI Agent HandbookMachine LearningSoftware Engineering

Perception and Action: How AI Agents Sense

Jul 15, 2025·13 min read

Explains how AI agents perceive their environment through inputs, tool outputs, and memory.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

BERT Architecture: Embeddings, Attention and Encoder Layers

Jul 14, 2025·52 min read

Examines the BERT architecture in detail covering model sizes (Base vs Large), three-layer embedding system, bidirectional attention patterns.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

BERT Contextual Embeddings: Extraction and Use

Jul 13, 2025·53 min read

Covers BERT representation extraction with [CLS] token usage, layer selection strategies, pooling methods, and the frozen vs fine-tuned trade-off.

Open notebook

History of Language AIMachine LearningData, Analytics & AI

Stable Diffusion: Latent Text-to-Image Models

Jul 13, 2025·12 min read

Stable Diffusion generates images in a compressed latent space. Covers text conditioning, the denoising process, training, inference, and model accessibility.

Open notebook

AI Agent HandbookMachine LearningSoftware Engineering

Defining the Agent's Environment: Where AI Agents Operate

Jul 13, 2025·10 min read

Explains what an environment means for AI agents, from digital assistants to physical robots. Explains how environment shapes perception, actions.

Open notebook

Data, Analytics & AIMachine LearningLanguage AI Handbook

Prefix Language Modeling

Jul 12, 2025·40 min read

Covers prefix LM, the hybrid pretraining objective that enables bidirectional prefix understanding with autoregressive generation.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningMachine Learning from Scratch

LightGBM: Fast Gradient Boosting

Jul 12, 2025·52 min read

Covers LightGBM gradient boosting framework, including leaf-wise tree growth, histogram-based binning, GOSS sampling, exclusive feature bundling.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

Denoising Objectives: BART's Corruption Strategies for LLMs

Jul 11, 2025·47 min read

Explains how BART trains language models using diverse text corruptions including token deletion, shuffling, sentence permutation.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningHistory of Language AI

FlashAttention: IO-Aware Attention for Long Contexts

Jul 11, 2025·12 min read

Covers FlashAttention introduced in 2022. Explains how IO-aware attention computation enabled 2-4x speedup and 5-10x memory reduction.

Open notebook

AI Agent HandbookMachine LearningSoftware Engineering

Managing State Across Interactions: Agent State Lifecycle

Jul 11, 2025·13 min read

Explains how AI agents maintain continuity across sessions with ephemeral, session, and persistent state management.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

Replaced Token Detection

Jul 10, 2025·58 min read

Explains how replaced token detection trains language models 4x more efficiently than masked language modeling.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

Span Corruption: T5's Pretraining Objective for Seq2Seq

Jul 9, 2025·51 min read

Explains how span corruption works in T5, including span selection strategies, geometric distributions, sentinel tokens.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningMachine Learning from Scratch

CatBoost: Categorical Boosting

Jul 9, 2025·42 min read

Covers CatBoost (Categorical Boosting), including categorical feature handling, target statistics, symmetric trees, ordered boosting, regularization techniques.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningHistory of Language AI

CLIP: Contrastive Pretraining for Vision and Language

Jul 9, 2025·19 min read

Covers OpenAI's CLIP, the early vision-language model that enables zero-shot image classification through contrastive learning.

Open notebook

AI Agent HandbookSoftware EngineeringMachine Learning

Designing the Agent's Brain

Jul 9, 2025·14 min read

Structure AI agents with clear architecture patterns. Build organized agent loops, decision logic.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

Whole Word Masking for BERT Pretraining

Jul 8, 2025·54 min read

Explains how Whole Word Masking improves BERT pre-training by masking complete words instead of subword tokens.

Open notebook

Data, Analytics & AILanguage AI HandbookMachine Learning

Masked Language Modeling

Jul 7, 2025·49 min read

Explains how masked language modeling enables bidirectional context understanding. Topics include the MLM objective, 15% masking rate, 80-10-10 strategy.

Open notebook

Data, Analytics & AISoftware EngineeringMachine LearningHistory of Language AI