Related papers: Versatile Ordering Network: An Attention-based Neu…

Ordinal regression (OR) is a special multiclass classification problem where an order relation exists among the labels. Recent years, people share their opinions and sentimental judgments conveniently with social networks and E-Commerce so…

Graph representation learning has achieved a remarkable success in many graph-based applications, such as node classification, link prediction, and community detection. These models are usually designed to preserve the vertex information at…

Topology Optimization (TO) provides a systematic approach for obtaining structure design with optimum performance of interest. However, the process requires numerical evaluation of objective function and constraints at each iteration, which…

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their…

We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as…

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two…

The problem of relevance ranking consists of sorting a set of objects with respect to a given criterion. Since users may prefer different relevance criteria, the ranking algorithms should be adaptable to the user needs. Two main approaches…

Unlike the conventional first-order network (FoN), the higher-order network (HoN) provides a more accurate description of transitions by creating additional nodes to encode higher-order dependencies. However, there exists no visualization…

Learning-based methods are promising to plan robot motion without performing extensive search, which is needed by many non-learning approaches. Recently, Value Iteration Networks (VINs) received much interest since---in contrast to standard…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

We develop a novel optical neural network (ONN) framework which introduces a degree of scalar invariance to image classification estima- tion. Taking a hint from the human eye, which has higher resolution near the center of the retina,…

Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. A natural way of modeling functional data is by learning operators…

Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of…

Deep Convolutional Neural Networks (CNNs) have been repeatedly proven to perform well on image classification tasks. Object detection methods, however, are still in need of significant improvements. In this paper, we propose a new framework…

Learning from the multidimensional data has been an interesting concept in the field of machine learning. However, such learning can be difficult, complex, expensive because of expensive data processing, manipulations as the number of…

We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning. Similar to Bayesian methods, VAN…

Assortment optimization seeks to select a subset of substitutable products, subject to constraints, to maximize expected revenue. The problem is NP-hard due to its combinatorial and nonlinear nature and arises frequently in industries such…

Discriminative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs. It has become the go-to methodology for tackling image restoration and…

Estimating free energy is a fundamental problem in statistical mechanics. Recently, machine-learning-based methods, particularly the variational autoregressive networks (VANs) have been proposed to minimize variational free energy and to…

Best-of-N (BoN) is a popular and effective algorithm for aligning language models to human preferences. The algorithm works as follows: at inference time, N samples are drawn from the language model, and the sample with the highest reward,…