In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if
harnessed appropriately, may deliver the best of expectations over many application sectors …

Highlights•Artificial and biological neural networks can be analyzed using similar
methods.•Neural analysis has revealed similarities between the representations in artificial …

Abstract Out-of-distribution (OOD) detection has received much attention lately due to its
practical importance in enhancing the safe deployment of neural networks. One of the …

Transfer learning–ie, further fine-tuning a pre-trained model on a downstream task–can
confer significant advantages, including improved downstream performance, faster …

Universality is a key hypothesis in mechanistic interpretability–that different models learn
similar features and circuits when trained on similar tasks. In this work, we study the …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

An important research direction in machine learning has centered around developing meta-
learning algorithms to tackle few-shot learning. An especially successful algorithm has been …

Recent work has sought to understand the behavior of neural networks by comparing
representations between layers and between different trained models. We examine methods …

Abstract We propose the Quantization Model of neural scaling laws, explaining both the
observed power law dropoff of loss with model and data size, and also the sudden …

With the growing use of graph convolutional neural networks (GCNNs) comes the need for
explainability. In this paper, we introduce explainability methods for GCNNs. We develop the …