arXiv subjects

Li Deng

Publications and source records attributed to Li Deng.

At least 55 records · Page 3Linked to original sources

arXiv2020

Second order necessary conditions for optimal control problems with endpoints-constraints and convex control-constraints

In this manuscript, we consider a control system governed by a general ordinary differential equation on a Riemannian manifold, with its endpoints satisfying some inequalities and equalities, and its control constrained to a closed convex set. We concern on an optimal control problem of this system, and obtain the second order necessary condition in the sense of convex variation (Theorem 2.2). To this end, we first obtain a second order necessary condition of an optimization problem (Theorem 4.2) via separation theorem of convex sets. Then, we derive our necessary condition by transforming the optimal control problem into an optimization problem. It is worth to point out that, our necessary condtition evolves the curvature tensor, which is trivial in Euclidean case. Moreover, even M is a Euclidean space, our result is still of interest. Actually, we give an example (Example 2.1) which shows that, when an optimal control stays at the boundary of the control set, the existing results are invalid while Theorem 2.2 works.

math.OC↗

arXiv2020

Discovering the Sky at the Longest wavelengths with a lunar orbit array

Due to ionosphere absorption and the interference by natural and artificial radio emissions, astronomical observation from the ground becomes very difficult at the wavelengths of decametre or longer, which we shall refer as the ultralong wavelengths. This unexplored part of electromagnetic spectrum has the potential of great discoveries, notably in the study of cosmic dark ages and dawn, but also in heliophysics and space weather, planets and exoplanets, cosmic ray and neutrinos, pulsar and interstellar medium (ISM), extragalactic radio sources, and so on. The difficulty of the ionosphere can be overcome by space observation, and the Moon can shield the radio frequency interferences (RFIs) from the Earth. A lunar orbit array can be a practical first step of opening up the ultralong wave band. Compared with a lunar surface observatory on the far side, the lunar orbit array is simpler and more economical, as it does not need to make the risky and expensive landing, can be easily powered with solar energy, and the data can be transmitted back to the Earth when it is on the near-side part of the orbit. Here I describe the Discovering Sky at the Longest wavelength (DSL) project, which will consist of a mother satellite and 6~9 daughter satellites, flying on the same circular orbit around the Moon, and forming a linear interferometer array. The data are collected by the mother satellite which computes the interferometric cross-correlations (visibilities) and transmits the data back to the Earth. The whole array can be deployed on the lunar orbit with a single rocket launch. The project is under intensive study in China.

astro-ph.IM↗

arXiv2020

Second Order Necessary Conditions for Endpoints-Constrained Optimal Control Problems on Riemannian manifolds

In this paper, we are concerned with optimal control problems evolved on Riemannian manifolds, where the initial and final states satisfy some inequality and equality type constraints, and the control set is a separable metric space. We obtain the second order necessary conditions of integral and quasi-pointwise forms, both of which work for Pontryagin type critical controls and involve the curvature tensor. Also, we apply the condition of integral form to the Bolza problem, where the initial and final states are subject to equality's type constraint.

math.OC↗

arXiv2020

Multimodal Intelligence: Representation Learning, Information Fusion, and Applications

Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial intelligence field involve multiple modalities. Therefore, it is of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, we provide a technical review of available models and learning methods for multimodal intelligence. The main focus of this review is the combination of vision and natural language modalities, which has become an important topic in both the computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications. Regarding multimodal representation learning, we review the key concepts of embedding, which unify multimodal signals into a single vector space and thereby enable cross-modality signal processing. We also review the properties of many types of embeddings that are constructed and learned for general downstream tasks. Regarding multimodal fusion, this review focuses on special architectures for the integration of representations of unimodal signals for a particular task. Regarding applications, selected areas of a broad interest in the current literature are covered, including image-to-text caption generation, text-to-image generation, and visual question answering. We believe that this review will facilitate future studies in the emerging field of multimodal intelligence for related communities.

cs.AI↗

arXiv2019

Discovering the Sky at the Longest Wavelengths with Small Satellite Constellations

Due to ionosphere absorption and the interference by natural and artificial radio emissions, ground observation of the sky at the decameter or longer is very difficult. This unexplored part of electromagnetic spectrum has the potential of great discoveries, notably in the study of cosmic dark ages and dawn, but also in heliophysics and space weather, planets, cosmic ray and neutrinos, pulsar and interstellar medium, extragalactic radio sources, and even SETI. At a forum organized by the International Space Science Institute-Beijing (ISSI-BJ), we discussed the prospect of opening up this window for astronomical observations by using a constellation of small or micro-satellites. We discussed the past experiments and the current ones such as the low frequency payload on Chang'e-4 mission lander, relay satellite and the Longjiang satellite, and also the future DSL mission, which is a linear array on lunar orbit which can make synthesized map of the whole sky as well as measure the global spectrum. We also discuss the synergy with other experiments, including ground global experiments such as EDGES, SARAS, SCI-HI and High-z, PRIZM/Albatros, ground imaging facillities such as LOFAR and MWA, and space experiments such as SUNRISE, DARE/DAPPER and PRATUSH. We also discussed some technical aspects of the DSL concept.

astro-ph.IM↗

arXiv2019

From Caesar Cipher to Unsupervised Learning: A New Method for Classifier Parameter Estimation

Many important classification problems, such as object classification, speech recognition, and machine translation, have been tackled by the supervised learning paradigm in the past, where training corpora of parallel input-output pairs are required with high cost. To remove the need for the parallel training corpora has practical significance for real-world applications, and it is one of the main goals of unsupervised learning. Recently, encouraging progress in unsupervised learning for solving such classification problems has been made and the nature of the challenges has been clarified. In this article, we review this progress and disseminate a class of promising new methods to facilitate understanding the methods for machine learning researchers. In particular, we emphasize the key information that enables the success of unsupervised learning - the sequential statistics as the distributional prior in the labels. Exploitation of such sequential statistics makes it possible to estimate parameters of classifiers without the need of paired input-output data. In this paper, we first introduce the concept of Caesar Cipher and its decryption, which motivated the construction of the novel loss function for unsupervised learning we use throughout the paper. Then we use a simple but representative binary classification task as an example to derive and describe the unsupervised learning algorithm in a step-by-step, easy-to-understand fashion. We include two cases, one with Bigram language model as the sequential statistics for use in unsupervised parameter estimation, and another with a simpler Unigram language model. For both cases, detailed derivation steps for the learning algorithm are included. Further, a summary table compares computational steps of the two cases in executing the unsupervised learning algorithm for learning binary classifiers.

cs.LG↗

arXiv2019

Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval

Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells, for training word and entity embeddings. These embeddings are then utilized in three particular table-related tasks, row population, column population, and table retrieval, by incorporating them into existing retrieval models as additional semantic similarity signals. Evaluation results show that table embeddings can significantly improve upon the performance of state-of-the-art baselines.

cs.IR↗

arXiv2018

Attentive Tensor Product Learning

This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, aiming to integrate deep learning with explicit language structures and rules. The key ideas of ATPL are: 1) unsupervised learning of role-unbinding vectors of words via TPR-based deep neural network; 2) employing attention modules to compute TPR; and 3) integration of TPR with typical deep learning architectures including Long Short-Term Memory (LSTM) and Feedforward Neural Network (FFNN). The novelty of our approach lies in its ability to extract the grammatical structure of a sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. This ATPL approach is applied to 1) image captioning, 2) part of speech (POS) tagging, and 3) constituency parsing of a sentence. Experimental results demonstrate the effectiveness of the proposed approach.

cs.CL↗

arXiv2018

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

We introduce a large scale MAchine Reading COmprehension dataset, which we name MS MARCO. The dataset comprises of 1,010,916 anonymized questions---sampled from Bing's search query logs---each with a human generated answer and 182,669 completely human rewritten generated answers. In addition, the dataset contains 8,841,823 passages---extracted from 3,563,535 web documents retrieved by Bing---that provide the information necessary for curating the natural language answers. A question in the MS MARCO dataset may have multiple answers or no answers at all. Using this dataset, we propose three different tasks with varying levels of difficulty: (i) predict if a question is answerable given a set of context passages, and extract and synthesize the answer as a human would (ii) generate a well-formed answer (if possible) based on the context passages that can be understood with the question and passage context, and finally (iii) rank a set of retrieved passages given a question. The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering. We believe that the scale and the real-world nature of this dataset makes it attractive for benchmarking machine reading comprehension and question-answering models.

cs.CL↗

arXiv2018

A Neural-Symbolic Approach to Design of CAPTCHA

CAPTCHAs based on reading text are susceptible to machine-learning-based attacks due to recent significant advances in deep learning (DL). To address this, this paper promotes image/visual captioning based CAPTCHAs, which is robust against machine-learning-based attacks. To develop image/visual-captioning-based CAPTCHAs, this paper proposes a new image captioning architecture by exploiting tensor product representations (TPR), a structured neural-symbolic framework developed in cognitive science over the past 20 years, with the aim of integrating DL with explicit language structures and rules. We call it the Tensor Product Generation Network (TPGN). The key ideas of TPGN are: 1) unsupervised learning of role-unbinding vectors of words via a TPR-based deep neural network, and 2) integration of TPR with typical DL architectures including Long Short-Term Memory (LSTM) models. The novelty of our approach lies in its ability to generate a sentence and extract partial grammatical structure of the sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. Experimental results demonstrate the effectiveness of the proposed approach.

cs.CL↗

arXiv2018

Towards Neural Phrase-based Machine Translation

In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new layer to perform (soft) local reordering of input sequences. Different from existing neural machine translation (NMT) approaches, NPMT does not use attention-based decoding mechanisms. Instead, it directly outputs phrases in a sequential order and can decode in linear time. Our experiments show that NPMT achieves superior performances on IWSLT 2014 German-English/English-German and IWSLT 2015 English-Vietnamese machine translation tasks compared with strong NMT baselines. We also observe that our method produces meaningful phrases in output languages.

cs.CL↗

arXiv2018

Sequence Modeling via Segmentations

Segmental structure is a common pattern in many types of sequences such as phrases in human languages. In this paper, we present a probabilistic model for sequences via their segmentations. The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment is modeled using existing tools such as recurrent neural networks. Since the segmentation of a sequence is usually unknown in advance, we sum over all valid segmentations to obtain the final probability for the sequence. An efficient dynamic programming algorithm is developed for forward and backward computations without resorting to any approximation. We demonstrate our approach on text segmentation and speech recognition tasks. In addition to quantitative results, we also show that our approach can discover meaningful segments in their respective application contexts.

stat.ML↗

arXiv2018

Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear

Many practical environments contain catastrophic states that an optimal agent would visit infrequently or never. Even on toy problems, Deep Reinforcement Learning (DRL) agents tend to periodically revisit these states upon forgetting their existence under a new policy. We introduce intrinsic fear (IF), a learned reward shaping that guards DRL agents against periodic catastrophes. IF agents possess a fear model trained to predict the probability of imminent catastrophe. This score is then used to penalize the Q-learning objective. Our theoretical analysis bounds the reduction in average return due to learning on the perturbed objective. We also prove robustness to classification errors. As a bonus, IF models tend to learn faster, owing to reward shaping. Experiments demonstrate that intrinsic-fear DQNs solve otherwise pathological environments and improve on several Atari games.

cs.LG↗

arXiv2017

Tensor Product Generation Networks for Deep NLP Modeling

We present a new approach to the design of deep networks for natural language processing (NLP), based on the general technique of Tensor Product Representations (TPRs) for encoding and processing symbol structures in distributed neural networks. A network architecture --- the Tensor Product Generation Network (TPGN) --- is proposed which is capable in principle of carrying out TPR computation, but which uses unconstrained deep learning to design its internal representations. Instantiated in a model for image-caption generation, TPGN outperforms LSTM baselines when evaluated on the COCO dataset. The TPR-capable structure enables interpretation of internal representations and operations, which prove to contain considerable grammatical content. Our caption-generation model can be interpreted as generating sequences of grammatical categories and retrieving words by their categories from a plan encoded as a distributed representation.

cs.CV↗

arXiv2017

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $ε$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.

cs.LG↗

arXiv2017

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as ε-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.

cs.AI↗

arXiv2017

Question-Answering with Grammatically-Interpretable Representations

We introduce an architecture, the Tensor Product Recurrent Network (TPRN). In our application of TPRN, internal representations learned by end-to-end optimization in a deep neural network performing a textual question-answering (QA) task can be interpreted using basic concepts from linguistic theory. No performance penalty need be paid for this increased interpretability: the proposed model performs comparably to a state-of-the-art system on the SQuAD QA task. The internal representation which is interpreted is a Tensor Product Representation: for each input word, the model selects a symbol to encode the word, and a role in which to place the symbol, and binds the two together. The selection is via soft attention. The overall interpretation is built from interpretations of the symbols, as recruited by the trained model, and interpretations of the roles as used by the model. We find support for our initial hypothesis that symbols can be interpreted as lexical-semantic word meanings, while roles can be interpreted as approximations of grammatical roles (or categories) such as subject, wh-word, determiner, etc. Fine-grained analysis reveals specific correspondences between the learned roles and parts of speech as assigned by a standard tagger (Toutanova et al. 2003), and finds several discrepancies in the model's favor. In this sense, the model learns significant aspects of grammar, after having been exposed solely to linguistically unannotated text, questions, and answers: no prior linguistic knowledge is given to the model. What is given is the means to build representations using symbols and roles, with an inductive bias favoring use of these in an approximately discrete manner.

cs.CL↗

arXiv2017

Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet). Given a high-performing MC model in one domain, our technique aims to answer questions about documents in another domain, where we use no labeled data of question-answer pairs. Using the proposed SynNet with a pretrained model from the SQuAD dataset on the challenging NewsQA dataset, we achieve an F1 measure of 44.3% with a single model and 46.6% with an ensemble, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-of-domain baseline of 7.6%, without use of provided annotations.

cs.CL↗