Research on nearest-neighbor methods tends to focus somewhat dichotomously either on the statistical or the computational aspects -- either on, say, Bayes consistency and rates of convergence or on techniques for speeding up the proximity search. This paper aims at bridging these realms: to reap the advantages of fast evaluation time while maintaining Bayes consistency, and further without sacrificing too much in the risk decay rate. We combine the locality-sensitive hashing (LSH) technique with a novel missing-mass argument to obtain a fast and Bayes-consistent classifier. Our algorithm's prediction runtime compares favorably against state of the art approximate NN methods, while maintaining Bayes-consistency and attaining rates comparable to minimax. On samples of size $n$ in $\R^d$, our pre-processing phase has runtime $O(d n \log n)$, while the evaluation phase has runtime $O(d\log n)$ per query point.

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, typical meta-learning models use shallow neural networks, thus limiting its effectiveness. In order to achieve top performance, some recent works tried to use the DNNs pre-trained on large-scale datasets but mostly in straight-forward manners, e.g., (1) taking their weights as a warm start of meta-training, and (2) freezing their convolutional layers as the feature extractor of base-learners. In this paper, we propose a novel approach called meta-transfer learning (MTL) which learns to transfer the weights of a deep NN for few-shot learning tasks. Specifically, meta refers to training multiple tasks, and transfer is achieved by learning scaling and shifting functions of DNN weights for each task. In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum that further boosts the learning efficiency of MTL. We conduct few-shot learning experiments and report top performance for five-class few-shot recognition tasks on three challenging benchmarks: miniImageNet, tieredImageNet and Fewshot-CIFAR100 (FC100). Extensive comparisons to related works validate that our MTL approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy.

Abstract: With the rapid growth in the number of scientific publications, year after year, it is becoming increasingly difficult to identify quality authoritative work on a single topic. Though there is an availability of scientometric measures which promise to offer a solution to this problem, these measures are mostly quantitative and rely, for instance, only on the number of times an article is cited. With this approach, it becomes irrelevant if an article is cited 10 times in a positive, negative or neutral way. In this context, it is quite important to study the qualitative aspect of a citation to understand its significance. This paper presents a novel system for sentiment analysis of citations in scientific documents (SentiCite) and is also capable of detecting nature of citations by targeting the motivation behind a citation, e.g., reference to a dataset, reading reference. Furthermore, the paper also presents two datasets (SentiCiteDB and IntentCiteDB) containing about 2,600 citations with their ground truth for sentiment and nature of citation. SentiCite along with other state-of-the-art methods for sentiment analysis are evaluated on the presented datasets. Evaluation results reveal that SentiCite outperforms state-of-the-art methods for sentiment analysis in scientific publications by achieving a F1-measure of 0.71. 1 INTRODUCTION Sentiment analysis is the process of computationally categorizing and identifying opinions present in a textual document or images. As a field, sentiment analysis has been gaining a lot of interest from the scientific community in recent years. The main motivation for this work comes from the author's observation that there is an unavailability of a system capable of automatically analyzing the sentiment present in citations of scientific publications.

A deep neural network has relieved the burden of feature engineering by human experts, but comparable efforts are instead required to determine an effective architecture. On the other hands, as the size of a network has over-grown, a lot of resources are also invested to reduce its size. These problems can be addressed by sparsification of an over-complete model, which removes redundant parameters or connections by pruning them away after training or encouraging them to become zero during training. In general, however, these approaches are not fully differentiable and interrupt an end-to-end training process with the stochastic gradient descent in that they require either a parameter selection or a soft-thresholding step. In this paper, we propose a fully differentiable sparsification method for deep neural networks, which allows parameters to be exactly zero during training, and thus can learn the sparsified structure and the weights of networks simultaneously using the stochastic gradient descent. We apply the proposed method to various popular models in order to show its effectiveness.

DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators Lu Lu 1, Pengzhan Jin 2, and George Em Karniadakis 1 1 Division of Applied Mathematics, Brown University, Providence, RI 02912, USA 2 LSEC, ICMSEC, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China Abstract While it is widely known that neural networks are universal approximators of continuous functions, a less known and perhaps more powerful result is that a neural network with a single hidden layer can approximate accurately any nonlinear continuous operator [5]. This universal approximation theorem is suggestive of the potential application of neural networks in learning nonlinear operators from data. However, the theorem guarantees only a small approximation error for a sufficient large network, and does not consider the important optimization and generalization errors. To realize this theorem in practice, we propose deep operator networks (DeepONets) to learn operators accurately and efficiently from a relatively small dataset. A DeepONet consists of two sub-networks, one for encoding the input function at a fixed number of sensorsx i,i 1,...,m (branch net), and another for encoding the locations for the output functions (trunk net). We perform systematic simulations for identifying two types of operators, i.e., dynamic systems and partial differential equations, and demonstrate that DeepONet significantly reduces the generalization error compared to the fully-connected networks. We also derive theoretically the dependence of the approximation error in terms of the number of sensors (where the input function is defined) as well as the input function type, and we verify the theorem with computational results. More importantly, we observe high-order error convergence in our computational tests, namely polynomial rates (from half order to fourth order) and even exponential convergence with respect to the training dataset size. 1 Introduction The universal approximation theorem states that neural networks can be used to approximate any continuous function to arbitrary accuracy if no constraint is placed on the width and depth of the hidden layers [7, 11]. However, another approximation result, which is yet more surprising and has not been appreciated so far, states that a neural network with a single hidden layer can approximate accurately any nonlinear continuous functional (a mapping from a space of functions into the real numbers) [3, 18, 25] or (nonlinear) operator (a mapping from a space of functions into another space of functions) [5, 4]. Before reviewing the approximation theorem for operators, we introduce some notation, which will be used through this paper. Let G be an operator taking an input functionu, and then G( u) is the corresponding output function.

Irrespective of the fact that Machine learning has produced groundbreaking results, it demands an enormous amount of data in order to perform so. Even though data production has been in its all-time high, almost all the data is unlabelled, hence making them unsuitable for training the algorithms. This paper proposes a novel method of extracting the features using Dynamic Mode Decomposition (DMD). The experiment is performed using data samples from Imagenet. The learning is done using SVM-linear, SVM-RBF, Random Kitchen Sink approach (RKS). The results have shown that DMD features with RKS give competing results.

Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical models have usually not worked that much better than their traditional seq2seq counterparts. This effect is mainly because either the hierarchical attention mechanisms are too sparse using hard attention or noisy using soft attention. In this paper, we propose a method based on extracting the highlights of a document; a key concept that is conveyed in a few sentences. In a typical text summarization dataset consisting of documents that are 800 tokens in length (average), capturing long-term dependencies is very important, e.g., the last sentence can be grouped with the first sentence of a document to form a summary. LSTMs (Long Short-Term Memory) proved useful for machine translation. However, they often fail to capture long-term dependencies while modeling long sequences. To address these issues, we have adapted Neural Semantic Encoders (NSE) to text summarization, a class of memory-augmented neural networks by improving its functionalities and proposed a novel hierarchical NSE that outperforms similar previous models significantly. The quality of summarization was improved by augmenting linguistic factors, namely lemma, and Part-of-Speech (PoS) tags, to each word in the dataset for improved vocabulary coverage and generalization. The hierarchical NSE model on factored dataset outperformed the state-of-the-art by nearly 4 ROUGE points. We further designed and used the first GPU-based self-critical Reinforcement Learning model.

With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YOLO is generally considered as one of the faster object detectors for low-end devices and is the basis for our work. Our experiments on this network have shown that Tiny-YOLO can achieve 0.14 frames per second(FPS) on the Raspberry Pi 3 B, which is too slow for soccer playing autonomous humanoid robots detecting goal and ball objects. In this paper we propose an adaptation to the YOLO CNN model named xYOLO, that can achieve object detection at a speed of 9.66 FPS on the Raspberry Pi 3 B. This is achieved by trading an acceptable amount of accuracy, making the network approximately 70 times faster than Tiny-YOLO. Greater inference speed-ups were also achieved on a desktop CPU and GPU. Additionally we contribute an annotated Darknet dataset for goal and ball detection.

It is important to collect credible training samples $(x,y)$ for building data-intensive learning systems (e.g., a deep learning system). In the literature, there is a line of studies on eliciting distributional information from self-interested agents who hold a relevant information. Asking people to report complex distribution $p(x)$, though theoretically viable, is challenging in practice. This is primarily due to the heavy cognitive loads required for human agents to reason and report this high dimensional information. Consider the example where we are interested in building an image classifier via first collecting a certain category of high-dimensional image data. While classical elicitation results apply to eliciting a complex and generative (and continuous) distribution $p(x)$ for this image data, we are interested in eliciting samples $x_i \sim p(x)$ from agents. This paper introduces a deep learning aided method to incentivize credible sample contributions from selfish and rational agents. The challenge to do so is to design an incentive-compatible score function to score each reported sample to induce truthful reports, instead of an arbitrary or even adversarial one. We show that with accurate estimation of a certain $f$-divergence function we are able to achieve approximate incentive compatibility in eliciting truthful samples. We then present an efficient estimator with theoretical guarantee via studying the variational forms of $f$-divergence function. Our work complements the literature of information elicitation via introducing the problem of \emph{sample elicitation}. We also show a connection between this sample elicitation problem and $f$-GAN, and how this connection can help reconstruct an estimator of the distribution based on collected samples.

However, it is notoriously di fficult to solve in practice, because IPMs memory requirements scale at a demanding rate. Indeed, state-of-the-art SDO solvers such as MOSEK cannot solve constrained instances of Problem (1) with n 250 variables on a standard laptop, and it is optimization folklore that there is a gap between SDOs theoretical and practical tractability. Motivated by the demanding memory requirements of IPMs, a stream of literature studies inexact methods for SDOs, which replace the semidefinite constraint with weaker yet less computationally demanding constraints. This approach was first investigated by Kim and Kojima [13], who observed that relaxing a positive semidefinite constraint to the weaker constraint that all 2 2 minors of a matrix are positive semidefinite yields a second order cone (SOC)-representable outer approximation of the positive semidefinite (PSD) cone. In a related line of work, Krishnan and Mitchell [15] propose applying Kelley [12]'s cutting plane method to generate