stochastic

Governed by probability rather than determined exactly; describing quantities, processes or algorithms that involve randomness. A stochastic process is a collection of random variablesrandom variable, n.: A quantity whose value depends on chance, such as the number rolled on a die or the next word a chatbot will write. indexed by time or space — Markov chainsMarkov chain, n.: A chance-driven process that moves between states without memory: the odds of its next move are set by where it is, never by the path that led there. Forecasting tomorrow's weather from today's alone is a simple example., random walks, Brownian motion and the stochastic differential equations behind diffusion modelsdiffusion model, n.: An AI that learns to create images, sound or video by practicing noise removal: shown pictures buried under static, it learns to clean them up, then builds new ones starting from pure static. are examples. In machine learning the word marks randomness that is deliberate or unavoidable: stochastic gradient descentstochastic gradient descent, n.: A faster version of gradient descent that estimates which way is downhill from a small random sample of the training data at each step, instead of checking the whole dataset. estimates gradients from random mini-batchesmini-batch, n.: A small random handful of training examples that a model learns from in a single step. Training works through many such handfuls instead of studying the whole dataset at once.; dropoutdropout, n.: A training trick that randomly switches off a fraction of a network's neurons at each step, so the network cannot lean too heavily on any one of them and learns sturdier patterns. and data augmentationdata augmentation, n.: Creating extra training examples by changing existing ones in ways that keep their meaning — a flipped, cropped or recolored photo of a cat still shows a cat — so the model learns more robustly. inject noise; reinforcement learningreinforcement learning, n.: A way of teaching a computer program by trial and error: it tries actions, earns points for good results and penalties for bad ones, and gradually learns which choices pay off over time. policies may choose actions at random; and language modelslarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. generate text by samplingsampling, n.: Picking some items at random from a larger set or from a range of possibilities — surveying 1,000 voters, say, or letting an AI choose its next word by a weighted lottery., so outputs vary between runs unless decoding is deterministic. Random initialization, data order and parallel floating-point arithmetic add further variation (see nondeterminismnondeterminism, n.: The fact that an AI model can give different answers to exactly the same question, partly because it deliberately chooses words with some randomness and partly because of tiny computing differences.). Stochastic does not mean arbitrary: the variation follows distributions that can be measured and controlled.

Because the grader is stochastic, we score every answer three times and take the majority.