Related papers: Synaptic Activation and Dual Liquid Dynamics for I…
The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner…
Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with…
Interpretability researchers have attempted to understand MLP neurons of language models based on both the contexts in which they activate and their output weight vectors. They have paid little attention to a complementary aspect: the…
We present an interpretability framework for unsupervised reinforcement learning (URL) agents, aimed at understanding how intrinsic motivation shapes attention, behavior, and representation learning. We analyze five agents DQN, RND, ICM,…
Deep neural networks (DNNs) are powerful black-box predictors that have achieved impressive performance on a wide variety of tasks. However, their accuracy comes at the cost of intelligibility: it is usually unclear how they make their…
The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…
Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability,…
While deep neural networks (DNNs) have become a standard architecture for many machine learning tasks, their internal decision-making process and general interpretability is still poorly understood. Conversely, common decision trees are…
Cellular traffic forecasting is a critical task that enables network operators to efficiently allocate resources and address anomalies in rapidly evolving environments. The exponential growth of data collected from base stations poses…
Fluidic iontronics offer a unique capability for emulating the chemical processes found in neurons. We extract multiple distinct chemically regulated synaptic features from an experimentally accessible conical microfluidic channel carrying…
A perturbative method is developed for calculating the effects of recurrent synaptic interactions between neurons embedded in a network. A series expansion is constructed that converges for networks with noisy membrane potential and weak…
As Transformers have become state-of-the-art models for natural language processing (NLP) tasks, the need to understand and explain their predictions is increasingly apparent. Especially in unsupervised applications, such as information…
Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc explanations, which may not suffice in high-stakes scenarios…
Recent advances in recurrent neural network architectures, such as Mamba and RWKV, have enabled RNNs to match or exceed the performance of equal-size transformers in terms of language modeling perplexity and downstream evaluations,…
Controlling the flow and routing of data is a fundamental problem in many distributed networks, including transportation systems, integrated circuits, and the Internet. In the brain, synaptic plasticity rules have been discovered that…
Deep neural networks excel in mapping genomic DNA sequences to associated readouts (e.g., protein-DNA binding). Beyond prediction, the goal of these networks is to reveal to scientists the underlying motifs (and their syntax) which drive…
The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN)…
Spiking neural networks (SNNs) have captured apparent interest over the recent years, stemming from neuroscience and reaching the field of artificial intelligence. However, due to their nature SNNs remain far behind in achieving the…
Spiking Neural Networks (SNNs) are promising brain-inspired models known for low power consumption and superior potential for temporal processing, but identifying suitable learning mechanisms remains a challenge. Despite the presence of…
Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with…