no code implementations • 22 Dec 2023 • Alexander Grushin
In this paper, we take the view that true intelligence may require the ability of a machine learning model to manage internal state, but that we have not yet discovered the most effective algorithms for training such models.
no code implementations • 25 Jul 2023 • Alexander Grushin, Walt Woods, Alvaro Velasquez, Simon Khan
Proxy criticality metrics that are computable in real-time (i. e., without actually simulating the effects of random actions) can be compared to the true criticality, and we show how to leverage these proxy metrics to generate safety margins, which directly tie the consequences of potentially incorrect actions to an anticipated loss in overall performance.
no code implementations • 30 Jul 2021 • Alexander Grushin, Walt Woods
However, this also presents a limitation: because the trained neural network can successfully parse any sentence, it cannot be directly used to identify sentences that deviate from the format of the training sentences, i. e., that are anomalous.