Home›Concepts
Concepts
Concepts
How AI works, in plain language: from the artificial neuron to the Transformer, pre-training and reasoning models.
Total 23 · Clear filters
Connectionist Temporal ClassificationConnectionist temporal classification (CTC) is a method for training recurrent neural networks to label unsegmented sequences, such as speech or handwriting, without frame-by-frame alignment. Introduced in 2006, it let CTC-trained LSTMs win the first international contests for recurrent networks.Deep learning on GPUsGraphics processing units (GPUs) run many arithmetic operations in parallel, which suits neural-network training. Their use from 2010 onward made deep learning practical at much larger scales.Xavier (Glorot) initializationXavier (Glorot) initialization is a weight-initialization scheme from Glorot and Bengio's 2010 paper that sets each layer's starting weight scale so signals stay stable across layers, giving substantially faster convergence in deep feedforward networks.Knowledge distillationKnowledge distillation trains a small model to reproduce the outputs of a larger model or an ensemble, so that much of the predictive performance is kept at lower compute and deployment cost.Mixture of experts (MoE)A mixture of experts model contains many sub-networks but routes each token to only a few of them. This lets total model size grow while the compute spent on each token stays much smaller than the total.Tensor CoresTensor Cores are specialised units inside NVIDIA GPUs that perform a small matrix multiply-and-add in one step, making the matrix arithmetic behind neural-network training and inference dramatically faster.Model parallelismModel parallelism splits one model's parameters and computation across multiple accelerators, so networks too large for a single device can still be trained. NVIDIA's 2019 Megatron-LM paper showed an intra-layer version built in native PyTorch.Scaling lawsScaling laws are empirical trends showing that a language model's test loss falls smoothly, as a power law, when parameters, data and training compute grow. They help plan large training runs and explain the race for compute.LoRA (low-rank adaptation)LoRA (low-rank adaptation) is a fine-tuning technique that freezes a pre-trained model's weights and trains small low-rank matrices instead, cutting the number of trainable parameters and the memory needed while keeping quality close to full fine-tuning.Speculative decodingSpeculative decoding speeds up text generation from large autoregressive models: a smaller model proposes several tokens and the large model checks them in parallel, producing identical output faster.Test-time computeTest-time compute is the computation a model spends while answering a prompt, beyond what training already fixed into its weights. A 2024 study by Snell et al. showed how to spend it adaptively, and how it can stand in for a bigger model.Computer useComputer use is an Anthropic capability, released in public beta in October 2024, that lets an AI model operate a computer the way a person does — reading the screen, moving a cursor, clicking and typing — so it can drive ordinary software built for humans.Vision-Language-Action model (VLA)A vision-language-action model (VLA) is a robot policy that takes in camera images and a language instruction and outputs actions directly, usually by adapting a pretrained vision-language model to control.Sim-to-real transferSim-to-real transfer is the practice of training robot policies in simulation and then adapting them to physical robots, using synthetic data to supplement costly real-world demonstrations.Feature engineeringFeature engineering is the preprocessing step that turns raw data into more useful inputs for machine learning and statistical models, shaping, cleaning and trimming the attributes a model learns from.Context windowA context window is the full span of text a model can refer to while producing a response, measured in tokens and including the response itself. Its size, and how evenly a model uses it, shape what the model can do.QuantizationQuantization stores a language model's weights and activations at lower numerical precision, cutting the memory and bandwidth that inference requires. Methods such as LLM.int8() and GPTQ made very large models runnable on far smaller hardware.KV cacheA KV cache keeps the key and value vectors a model has already computed for earlier tokens, so each new token reuses them instead of recomputing. Its memory footprint is what makes high-throughput serving hard to scale.Prompt engineeringPrompt engineering is the practice of designing the text input that steers a generative AI system toward a desired output. Shared vocabulary and techniques such as chain-of-thought prompting make results easier to describe, compare and reproduce.Synthetic dataSynthetic data is training material written by a model rather than collected from people or the web. In the phi-1 experiments a small code model trained partly on model-generated "textbooks" reached competitive benchmark scores, suggesting data quality itself shapes capability.