Amir Feder

TL;DR: This work defines the Causal Concept Effect (CaCE) as the causal effect of a human-interpretable concept on a deep neural net's predictions, and shows that the CaCE measure can avoid errors stemming from confounding.

TL;DR: This article showed that the human brain and autoregressive DLMs share three fundamental computational principles as they process the same natural narrative: (1) both are engaged in continuous next-word prediction before word onset; (2) both match their pre-onset predictions to the incoming word to calculate post-onset surprise; and (3) both rely on contextual embeddings to represent words in natural contexts.

TL;DR: CausaLM is proposed, a framework for producing causal model explanations using counterfactual language representation models based on fine-tuning of deep contextualized embedding models with auxiliary adversarial tasks derived from the causal graph of the problem.

TL;DR: It is found that following DDoS attacks on Mt. Gox, the number of large trades on the exchange fell sharply, and the distribution of the daily trading volume becomes less skewed (fewer big trades) and had smaller kurtosis on days followingDDoS attacks.

TL;DR: Empirical evidence is provided that the human brain and autoregressive DLMs share two computational principles: both are engaged in continuous prediction; both represent words as a function of the previous context; and DLM’s contextual embeddings capture the neural representation of context-specific word meaning better than arbitrary or static semantic embedding.