Unverified50% confidenceFactExact time
RNN及其变体LSTM和GRU按时间步依次处理序列，存在梯度指数级衰减导致长距离依赖捕捉困难，以及无法并行化训练的缺陷
1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
Getting Started with LLMs: A Complete Roadmap from Zero to Practice
bilibili凉也要学AI7/3/2026
Related Claims
UnverifiedRNNs suffer from vanishing/exploding gradient problems, where gradients propagating across a large number of time steps decay or grow exponentially, making it difficult to learn long-range dependencies.81% similarUnverifiedThe core defect of RNNs (Recurrent Neural Networks) lies in their sequential computation nature, which requires processing sequences one time step at a time, causing long-range dependencies to decay exponentially with sequence length.76% similarUnverified传统 RNN 架构因顺序处理的局限在面对远距离依赖时会出现梯度消失问题76% similarUnverifiedRNN存在两大缺陷：无法并行计算导致速度慢，以及长距离依赖信息衰减的健忘问题75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/113949API
curl https://kongchang.com/api/v1/knowledge/claims/113949MCP
get_claim(id=113949)