Related papers: Deriving Machine Attention from Human Rationales

The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse…

The application of computer vision is gradually increasing across various domains. They employ deep learning models with a black-box nature. Without the ability to explain the behavior of neural networks, especially their decision-making…

Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during…

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Past work has long recognized the important role of context in guiding how humans search their memory. While context-based memory models can explain many memory phenomena, it remains unclear why humans develop such architectures over…

Image classification models have achieved satisfactory performance on many datasets, sometimes even better than human. However, The model attention is unclear since the lack of interpretability. This paper investigates the fidelity and…

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of…

Attention control is a key cognitive ability for humans to select information relevant to the current task. This paper develops a computational model of attention and an algorithm for attention-based probabilistic planning in Markov…

Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more on the essential aspects of data. Deep learning has employed…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

Effective communication requires adapting to the idiosyncrasies of each communicative context--such as the common ground shared with each partner. Humans demonstrate this ability to specialize to their audience in many contexts, such as the…

Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios. One of the most popular and fascinating approaches relies on learning vehicle…

One of the common ways children learn is by mimicking adults. Imitation learning focuses on learning policies with suitable performance from demonstrations generated by an expert, with an unspecified performance measure, and unobserved…

Current language models often fail to incorporate long contexts efficiently during generation. We show that a major contributor to this issue are attention priors that are likely learned during pre-training: relevant information located…

The in-context learning capabilities of modern language models have motivated a deeper mathematical understanding of sequence models. A line of recent work has shown that linear attention models can emulate projected gradient descent…

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic…

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and…

Attention-based mechanisms are widely used in machine learning, most prominently in transformers. However, hyperparameters such as the rank of the attention matrices and the number of heads are scaled nearly the same way in all realizations…