Related papers: Know2Vec: A Black-Box Proxy for Neural Network Ret…

Humans learn to solve tasks of increasing complexity by building on top of previously acquired knowledge. Typically, there exists a natural progression in the tasks that we learn - most do not require completely independent solutions, but…

Referring Expression Comprehension (REC) is a popular multimodal task that aims to accurately detect target objects within a single image based on a given textual expression. However, due to the limitations of earlier models, traditional…

Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans…

This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we…

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined…

From self-driving vehicles and back-flipping robots to virtual assistants who book our next appointment at the hair salon or at that restaurant for dinner - machine learning systems are becoming increasingly ubiquitous. The main reason for…

The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures. When a gold standard is available, performance assessment treats the DNN as a…

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…

Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrieval-based dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where…

Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to fixed points of neural networks, are of growing interest in the deep learning community. However, training and applying DEQ models is currently done in…

The following work presents how autoencoding all the possible hidden activations of a network for a given problem can provide insight about its structure, behavior, and vulnerabilities. The method, termed self-introspection, can show that a…

Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation. Commonly comprised of hundreds of millions of parameters, these neural network…

Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions that programmatically solve different…

Phylogenetics is a fundamental component of evolutionary analysis frameworks in biology and linguistics. Recently, the advent of large-scale genomics and the SARS-CoV-2 pandemic has highlighted the necessity for phylogenetic software to…

Real-world data usually have high dimensionality and it is important to mitigate the curse of dimensionality. High-dimensional data are usually in a coherent structure and make the data in relatively small true degrees of freedom. There are…

With the advent of deep learning, the number of works proposing new methods or improving existent ones has grown exponentially in the last years. In this scenario, "very deep" models were emerging, once they were expected to extract more…

The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack…

Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades,…

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single…

Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies,…