Machine Learning Primer
From the fundamentals of neural networks through reinforcement learning, object detection and recognition, and generative models, explained through both implementation and math.
Choose a path by its goals and prerequisites. Start at the beginning or jump to the topic you need.
Articles · 7Browser Labs · 1
Read the first step: Machine Learning Primer: Foundations — Designing Data, Loss, and Generalization →Background and reading guide Basic functions, probability and vectors.
- Articles · Fundamentals · 5 min
Machine Learning Primer: Foundations — Designing Data, Loss, and Generalization
Machine learning is not just model selection: define the task, data split, loss, evaluation, and deployment change.
Background and reading guide
Basic functions, probability and vectors.
- Articles · Fundamentals · 5 min
Machine Learning Primer: Neural Network Basics
Neural networks stack affine transforms and nonlinear activations, then reduce loss by backpropagation and gradient-based optimization.
Background and reading guide
Basic functions, probability and vectors.
- Articles · Fundamentals · 14 min
Object Detection & Semantic Segmentation Primer — Reading "What Is Where" From an Image
Object Detection draws boxes around things; Semantic Segmentation colors in every pixel by meaning. From the difference between the two, through Instance and Panoptic Segmentation, the lineage from R-CNN to YOLO, DETR and DINO, all the way to their 3D point-cloud counterparts — a systematic tour of the fundamentals of scene understanding.
Background and reading guide
Basic functions, probability and vectors.
- Articles · Fundamentals · 11 min
YOLO11 Explained in Depth — What Did C3k2 and C2PSA Change from YOLOv8?
Break down Ultralytics YOLO11 using official documentation and primary sources: C3k2, C2PSA, anchor-free detection, DFL/CIoU losses, and measured benchmarks for n/s/m/l/x.
Background and reading guide
Basic functions, probability and vectors.
- Articles · Fundamentals · 9 min
A Thorough Guide to SegFormer — Why a Transformer Without Positional Encoding Works for Segmentation
This article breaks down SegFormer, introduced by NVIDIA, The University of Hong Kong, and collaborators at NeurIPS 2021, based on the original paper. We examine the hierarchical MiT encoder without positional encoding, the parameter-efficient All-MLP decoder, the effective receptive field, and the measured mIoU, parameter counts, and compute from B0 to B5 with equations.
Background and reading guide
Basic functions, probability and vectors.
- Articles · Fundamentals · 4 min
Machine Learning Primer: Pose Estimation
Pose estimation infers human or object keypoints and 6D pose from images. This primer covers coordinates, losses, occlusion, evaluation, and safety.
Background and reading guide
Basic functions, probability and vectors.
- Articles · Fundamentals · 4 min
Machine Learning Primer: Generative Models
Generative models represent data distributions and create conditional outputs. Learn likelihood, VAE, GAN, diffusion, evaluation, provenance, and safety.
Background and reading guide
Basic functions, probability and vectors.
- Browser Labs · Hands-on · 3 min
Benchmark local LLMs: first response, generation rate and memory
Measure first answer content separately from generation rate and control residency, caching and memory conditions.
Background and reading guide
A browser for the synthetic Lab; Ollama and HTTP/Python knowledge only for optional real-endpoint measurements.