ДалееСледующее руководство
Графовые нейронные сети
Основы
РУКОВОДСТВО ПО ОСНОВАМ
A recurrent neural network updates an internal state while processing a sequence.
Прослушайте это руководствоОзвучено ИИ · ~3 min
That state can represent information from earlier steps, making ordered inputs useful without guaranteeing perfect retention of the full history.
A conventional unidirectional RNN combines the current input with its previous hidden state to produce a new hidden state. A separate output computation may produce a prediction, so the recurrent state should not automatically be called the previous prediction output. The state is an evolving representation rather than a complete lossless copy of everything encountered. Ordered data such as text, speech, and sensor time series can be modeled through this recurrent structure. Training commonly uses backpropagation through time, which views repeated recurrent computations as an unrolled dependency graph. Multiplying derivatives across many steps can lead to vanishing or exploding gradients, making long-distance dependency learning difficult. LSTM and GRU architectures use gates to regulate information flow. LSTM includes a cell state and input, forget, and output gating; gates can mitigate difficulties but do not guarantee perfect long-term memory. Attention-based transformer architectures offer more parallel computation across training positions and direct interactions among allowed positions. Autoregressive transformer generation can still proceed token by token, so parallel training should not be confused with completely parallel generation. A simple linear recurrence illustrates state updates: h-new equals one-half h-previous plus x. With h-previous two and x three, the new state is four. This is a stated illustration, not the complete nonlinear update of every RNN. A fixed-size recurrent inference state also differs from training memory, where storing or recomputing information across many steps creates additional costs.
Modeling a sequence of text tokens with an evolving hidden state.
Forecasting a defined sensor time series from earlier readings.
Studying gates in LSTM and GRU sequence models.
Comparing streaming inference state with memory used for training an unrolled sequence.
Recurrent, attention-based, and state-space approaches can be compared for particular sequence and streaming workloads. Measurements should identify whether they concern training or inference, the sequence length, state size, and task quality. A compact inference state can be useful while its limited representation may lose information. More parallel training or a gated design can change tradeoffs, but neither establishes universal superiority or perfect context retention. Evaluate the model and implementation on the intended inputs.
Бесплатная рассылка
Три проверенных AI-истории каждое утро буднего дня, написанные простым английским. Бесплатно навсегда, без рекламы.
Одно электронное письмо каждый будний день. Отписаться в один клик. Мы никогда не продаем и не передаем ваш адрес.
Проверьте себя
Мгновенная обратная связь по каждому ответу и общий сертификат с проверяемым идентификатором после прохождения курса.
Поддержите бесплатное образование в области искусственного интеллекта. AI Understanding — это некоммерческая организация 501(c)(3). Никакой рекламы и платного доступа. Сделать пожертвование
A recurrent neural network updates an internal state while processing a sequence. That state can represent information from earlier steps, making ordered inputs useful without guaranteeing perfect retention of the full history.
The hidden state participates in the next state update; it is distinct from a separately produced prediction.
A hidden state can carry useful information while losing details; it is not perfect permanent memory.
Long derivative products can become small or large, complicating learning of distant dependencies.
Закрытые подразделения, такие как LSTM и GRU, учатся регулировать поток информации, позволяя полезному контексту сохраняться в длинных последовательностях и уменьшая проблему исчезающего градиента.
RNN лучше всего подходят для упорядоченных данных, где важны контекст и последовательность, таких как предложения, аудиопотоки и измерения с течением времени.
Продолжайте учиться
Другие руководства, выбранные по этой теме
ДалееСледующее руководство
Графовые нейронные сети
Основы