Pith. sign in

REVIEW 2 cited by

Learning Longer Memory in Recurrent Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1412.7753 v2 pith:RWELO46L submitted 2014-12-24 cs.NE cs.LG

classification cs.NEcs.LG
keywords recurrentgradientlongermemorynetworksneuraltermdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this paper, we show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. We encourage some of the hidden units to change their state slowly by making part of the recurrent weight matrix close to identity, thus forming kind of a longer term memory. We evaluate our model in language modeling experiments, where we obtain similar performance to the much more complex Long Short Term Memory (LSTM) networks (Hochreiter & Schmidhuber, 1997).

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Spatiotemporal deep learning models for detection of rapid intensification in cyclones

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Adding LSTM-generated synthetic cyclone tracks to training data improves deep learning detection of rapid intensification events, but the gain is not compared with simpler baselines.

  2. Revisiting Glorot Initialization for Long-Range Linear Recurrences

    cs.LG 2025-05 reject novelty 5.0 of 10

    Glorot initialization is unstable for long-range linear RNNs because the spectral radius exceeds 1, with a proposed rescaling that helps in practice, but the theoretical claim that explosion starts at t = O(√n) is not...

Pith tools