相关论文: Hebbian Crosstalk and Input Segregation

The task of obfuscating writing style using sequence models has previously been investigated under the framework of obfuscation-by-transfer, where the input text is explicitly rewritten in another style. These approaches also often lead to…

In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same task. Given the limited availability of labelled examples in…

We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

Aspects of cell metabolism are modeled by ordinary differential equations describing the change of intracellular chemical concentrations. There is a correspondence between this dynamical system and a complex network. As in the classic…

Representation learning from complex data typically involves models with a large number of parameters, which in turn require large amounts of data samples. In neural network models, model complexity grows with the number of inputs to each…

The complex challenge of detecting sarcasm in Arabic speech on social media is increased by the language diversity and the nature of sarcastic expressions. There is a significant gap in the capability of existing models to effectively…

Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect of hierarchical…

In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we propose Multi-head Explicit Attention (MEA), a simple yet…

Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing high-level reasoning. Classical methods address this by…

Biases in automated clinical decision-making using Electronic Healthcare Records (EHR) impose significant disparities in patient care and treatment outcomes. Conventional approaches have primarily focused on bias mitigation strategies…

Temporal prediction is a still difficult task due to the chaotic behavior, non-Markovian characteristics, and non-stationary noise of temporal signals. Handwriting prediction is also challenging because of uncertainty arising from…

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. We take inspiration…

In the last two decades several biclustering methods have been developed as new unsupervised learning techniques to simultaneously cluster rows and columns of a data matrix. These algorithms play a central role in contemporary machine…

Specialized attention heads dubbed induction heads (IHs) have been argued to underlie the remarkable in-context learning capabilities of modern language models; yet, a precise characterization of their emergence, especially in the context…

We consider a neural field model which consists of a network of an arbitrary number of Wilson-Cowan nodes with homeostatic adjustment of the inhibitory coupling strength and time delayed, excitatory coupling. We extend previous work on this…

Over the past decade, deep neural networks have proven to be adept in image classification tasks, often surpassing humans in terms of accuracy. However, standard neural networks often fail to understand the concept of hierarchical…

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be…

Cross-lingual word embeddings aim to capture common linguistic regularities of different languages, which benefit various downstream tasks ranging from machine translation to transfer learning. Recently, it has been shown that these…

Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and…