Recently, a series of studies have tried to extract interactions between input variables
modeled by a DNN and define such interactions as concepts encoded by the DNN …

This paper theoretically explains the intuition that simple concepts are more likely to be
learned by deep neural networks (DNNs) than complex concepts. In fact, recent studies …

In this paper, we focus on mean-field variational Bayesian Neural Networks (BNNs) and
explore the representation capacity of such BNNs by investigating which types of concepts …

This paper aims to illustrate the concept-emerging phenomenon in a trained DNN.
Specifically, we find that the inference score of a DNN can be disentangled into the effects of …

This paper aims to prove the emergence of symbolic concepts in well-trained AI models. We
prove that if (1) the high-order derivatives of the model output wrt the input variables are all …

Self-attention mechanism is the key of the Transformer but often criticized for its computation
demands. Previous token pruning works motivate their methods from the view of …

Masking some input variables of a deep neural network (DNN) and computing output
changes on the masked input sample represent a typical way to compute attributions of input …

The advancement of the Internet of Things applications (technologies and enabling
platforms), consisting of software and hardware (eg, sensors, actuators, etc.), allows …

Multivariate time series classification (MTSC), which identifies categories of multiple sensor
signals recorded in continuous time, is widely used in various fields such as transportation …

In this paper, we explain the inference logic of large language models (LLMs) as a set of
symbolic concepts. Many recent studies have discovered that traditional DNNs usually …