Pith. sign in

REVIEW

Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent 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 1711.02326 v1 pith:IDS6QE63 submitted 2017-11-07 cs.AI cs.LGcs.NEstat.ML

classification cs.AIcs.LGcs.NEstat.ML
keywords backtrackingdependenciestimeattentivebackpropagationpastsparseused
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason, full backpropagation through time is rarely used on long sequences, and truncated backpropagation through time is used as a heuristic. However, this usually leads to biased estimates of the gradient in which longer term dependencies are ignored. Addressing this issue, we propose an alternative algorithm, Sparse Attentive Backtracking, which might also be related to principles used by brains to learn long-term dependencies. Sparse Attentive Backtracking learns an attention mechanism over the hidden states of the past and selectively backpropagates through paths with high attention weights. This allows the model to learn long term dependencies while only backtracking for a small number of time steps, not just from the recent past but also from attended relevant past states.

Discussion (0). Sign in to comment.

Pith tools