Search Results for author:
Found 9 papers, 3 papers with code
Towards Unbiased Exploration in Partial Label Learning
We consider learning a probabilistic classifier from partially-labelled supervision (inputs denoted with multiple possibilities) using standard neural architectures with a softmax as the final layer.
Lemmas: Generation, Selection, Application
Noting that lemmas are a key feature of mathematics, we engage in an investigation of the role of lemmas in automated theorem proving.
Safety without alignment
Currently, the dominant paradigm in AI safety is alignment with human values.
Towards solving the 7-in-a-row game
Our paper explores the game theoretic value of the 7-in-a-row game.
The Role of Entropy in Guiding a Connection Prover
This leads us to explore how the entropy of the inference selection implemented via the neural network influences the proof search.
Data-dependent Pruning to find the Winning Lottery Ticket
The Lottery Ticket Hypothesis postulates that a freshly initialized neural network contains a small subnetwork that can be trained in isolation to achieve similar performance as the full network.
Prolog Technology Reinforcement Learning Prover
We present a reinforcement learning toolkit for experiments with guiding automated theorem proving in the connection calculus.
Towards Finding Longer Proofs
We present a reinforcement learning (RL) based guidance system for automated theorem proving geared towards Finding Longer Proofs (FLoP).
Gradient Regularization Improves Accuracy of Discriminative Models
Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times.
