Related papers: Bottom-up Attention, Models of
The past two decades have witnessed a surge of new research in the analysis of randomized experiments. The emergence of this literature may seem surprising given the widespread use and long history of experiments as the "gold standard" in…
Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable…
Neuroscience research is undergoing a minor revolution. Recent advances in machine learning and artificial intelligence (AI) research have opened up new ways of thinking about neural computation. Many researchers are excited by the…
In the emerging era of big data, larger available clinical datasets and computational advances have sparked a massive interest in machine learning-based approaches. The number of manuscripts related to machine learning or artificial…
This article surveys recent progress in the Bradley-Terry (BT) model and its extensions. We focus on the statistical and computational aspects, with emphasis on the regime in which both the number of objects and the volume of comparisons…
In recent years, three-dimensional point clouds are used increasingly to document natural environments. Each dataset contains a diverse set of objects, at varying shapes and sizes, distributed throughout the data and intricately intertwined…
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…
Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…
Predictions and forecasts of machine learning models should take the form of probability distributions, aiming to increase the quantity of information communicated to end users. Although applications of probabilistic prediction and…
Stuttering is a complex disorder that requires specialized expertise for effective assessment and treatment. This paper presents an effort to enhance the FluencyBank dataset with a new stuttering annotation scheme based on established…
Neural activity forecasting is central to understanding neural systems and enabling closed-loop control. While deep learning has recently advanced the state-of-the-art in the time series forecasting literature, its application to neural…
Histopathological images contain rich phenotypic information that can be used to monitor underlying mechanisms contributing to diseases progression and patient survival outcomes. Recently, deep learning has become the mainstream…
In the NLP community, recent years have seen a surge of research activities that address machines' ability to perform deep language understanding which goes beyond what is explicitly stated in text, rather relying on reasoning and knowledge…
Large language models (LLMs) have made fundamental contributions over the last a few years. To train an LLM, one needs to alternatingly run `forward' computations and `backward' computations. The forward computation can be viewed as…
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden…
This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global,…
Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases an input salience method, which highlights the most important parts of the input, may reveal problematic…
Incorporating human domain knowledge for breast tumor diagnosis is challenging, since shape, boundary, curvature, intensity, or other common medical priors vary significantly across patients and cannot be employed. This work proposes a new…
This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…
Deep learning methods employ multiple processing layers to learn hierarchical representations of data and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context…