Pith. sign in

REVIEW 1 cited by

Constrained Feedforward Neural Network Training via Reachability Analysis

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 2107.07696 v1 pith:IUVOSR5K submitted 2021-07-16 cs.LG cs.AIcs.RO

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

Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural network to obey safety constraints. Most existing safety-related methods only seek to verify that already-trained networks obey constraints, requiring alternating training and verification. Instead, this work proposes a constrained method to simultaneously train and verify a feedforward neural network with rectified linear unit (ReLU) nonlinearities. Constraints are enforced by computing the network's output-space reachable set and ensuring that it does not intersect with unsafe sets; training is achieved by formulating a novel collision-check loss function between the reachable set and unsafe portions of the output space. The reachable and unsafe sets are represented by constrained zonotopes, a convex polytope representation that enables differentiable collision checking. The proposed method is demonstrated successfully on a network with one nonlinearity layer and approximately 50 parameters.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis

    cs.LG 2025-01 conditional novelty 6.0 of 10

    A new training method uses scaled hybrid zonotopes to turn exact ReLU reachability into a differentiable loss, enabling verified avoidance of non-convex unsafe sets.

Pith tools