斯坦福最新cs231n课程ppt-10

卷积神经网络 - RNNs allow a lot of flexibility in architecture design - Vanilla RNNs are simple but don’t work very well - Common to use LSTM or GRU: their additive interactions improve gradient flow - Backward flow of gradients in RNN can explode or vanish. Exploding is controlled with gradient clipping. Vanishing is controlled with additive interactions (LSTM) - Better/simpler architectures are a hot topic of current research - Better understanding (both theoretical and empirical) is needed.