Related papers: GLUScope: A Tool for Analyzing GLU Neurons in Tran…
A mechanistic understanding of how MLPs do computation in deep neural networks remains elusive. Current interpretability work can extract features from hidden activations over an input dataset but generally cannot explain how MLP weights…
The final MLP of GPT-2 Small exhibits a fully legible routing program -- 27 named neurons organized into a three-tier exception handler -- while the knowledge it routes remains entangled across ~3,040 residual neurons. We decompose all…
The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the…
We present GR-NLP-TOOLKIT, an open-source natural language processing (NLP) toolkit developed specifically for modern Greek. The toolkit provides state-of-the-art performance in five core NLP tasks, namely part-of-speech tagging,…
Deriving inference from heterogeneous inputs (such as images, text, and audio) is an important skill for humans to perform day-to-day tasks. A similar ability is desirable for the development of advanced Artificial Intelligence (AI)…
Neuroimaging studies are often limited by the number of subjects and cognitive processes that can be feasibly interrogated. However, a rapidly growing number of neuroscientific studies have collectively accumulated an extensive wealth of…
An activation function has crucial role in a deep neural network. A simple rectified linear unit (ReLU) are widely used for the activation function. In this paper, a weighted sigmoid gate unit (WiG) is proposed as the activation function.…
Selecting the most suitable activation function is a critical factor in the effectiveness of deep learning models, as it influences their learning capacity, stability, and computational efficiency. In recent years, the Gaussian Error Linear…
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…
Graph Neural Networks (GNNs) are widely used on a variety of graph-based machine learning tasks. For node-level tasks, GNNs have strong power to model the homophily property of graphs (i.e., connected nodes are more similar) while their…
Language-driven grasp detection has the potential to revolutionize human-robot interaction by allowing robots to understand and execute grasping tasks based on natural language commands. However, existing approaches face two key challenges.…
Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Knowledge graphs…
Neuroscientists apply a range of common analysis tools to recorded neural activity in order to glean insights into how neural circuits implement computations. Despite the fact that these tools shape the progress of the field as a whole, we…
Recent progress in cross-lingual relation and event extraction use graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations such that models trained on one language can be…
Recent work in vision-and-language demonstrates that large-scale pretraining can learn generalizable models that are efficiently transferable to downstream tasks. While this may improve dataset-scale aggregate metrics, analyzing performance…
Sign language recognition and translation first uses a recognition module to generate glosses from sign language videos and then employs a translation module to translate glosses into spoken sentences. Most existing works focus on the…
Biocomputing technologies exploit biological communication mechanisms involving cell-cell signal propagation to perform computations. Researchers recently worked toward realising logic gates made by neurons to develop novel devices such as…
Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for…
Deep Learning based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, introspection methods have been…
Visual Question Answering systems target answering open-ended textual questions given input images. They are a testbed for learning high-level reasoning with a primary use in HCI, for instance assistance for the visually impaired. Recent…