A neural network is a mathematical model loosely inspired by how biological brains work. It consists of layers of "neurons" — simple units that multiply their inputs by adjustable numbers called weights, sum the results, and pass them through an activation function.
How it learns
- The network starts with random weights and makes random predictions.
- For each training example, it measures how wrong its prediction was (the loss).
- Using backpropagation and gradient descent, it nudges every weight slightly in the direction that reduces the error.
- Repeated over thousands of examples and many epochs, the network discovers patterns in the data.
Common uses
- Classification (spam detection, image recognition, fraud detection)
- Prediction and forecasting
- Language understanding (the foundation of modern LLMs like GPT and Claude)
Try it yourself Our Neural Network Playground lets you train a real neural network in your browser — no code required — and watch the weights change as it learns.
Related Tools
Related Articles
View all articlesLocal LLM Benchmarks: 12 Findings From Consumer Hardware
NVIDIA publishes its inference wins on 8× DGX B300s. Almost nobody has those. So we ran the same ideas on a single consumer RTX 5060 Ti, a 2017 GTX 1080 Ti, and a CPU — and measured what actually happens. Here are all 12 experiments.
Read article →Ollama vs llama.cpp vs LM Studio: The Speed Tax, Measured
LM Studio, Ollama, and raw llama.cpp all run the same engine on the same GPU. We measured what the convenience layer costs: LM Studio adds 0.3%, Ollama adds 10%.
Read article →How Low Can You Quantize a GGUF Model Before Quality Breaks?
We swept Qwen2.5-Coder-7B from Q2 to Q8 on an RTX 5060 Ti. Output fidelity goes 21% at Q2, 57% at Q4, 80% at Q6 — the cliff is below Q4, and the sweet spot is Q4–Q5.
Read article →KV-Cache Quantization: The q4_0 Cliff Your Logs Won't Warn You About
We benchmarked f16 vs q8_0 vs q4_0 KV caches on the same model. q8_0 KV is nearly lossless (81.6% similar). q4_0 KV wrecks output quality (8.3%) while saving VRAM — and your throughput dashboard stays green the whole time.
Read article →Explore More Machine Learning
View all termsBackpropagation
The algorithm that calculates how much each weight in a neural network contributed to a prediction error, so every weight can be corrected.
Read more →Deep Learning
Machine learning using neural networks with multiple hidden layers, allowing models to learn increasingly abstract patterns from raw data.
Read more →Gradient Descent
The optimization algorithm that trains neural networks by repeatedly nudging weights in the direction that reduces prediction error.
Read more →