In recent years, the use of bio-sensing signals such as electroencephalogram (EEG), electrocardiogram (ECG), etc. have garnered interest towards applications in affective computing. The parallel trend of deep-learning has led to a huge leap in performance towards solving various vision-based research problems such as object detection. Yet, these advances in deep-learning have not adequately translated into bio-sensing research. This work applies novel deep-learning-based methods to various bio-sensing and video data of four publicly available multi-modal emotion datasets. For each dataset, we first individually evaluate the emotion-classification performance obtained by each modality. We then evaluate the performance obtained by fusing the features from these modalities. We show that our algorithms outperform the results reported by other studies for emotion/valence/arousal/liking classification on DEAP and MAHNOB-HCI datasets and set up benchmarks for the newer AMIGOS and DREAMER datasets. We also evaluate the performance of our algorithms by combining the datasets and by using transfer learning to show that the proposed method overcomes the inconsistencies between the datasets. Hence, we do a thorough analysis of multi-modal affective data from more than 120 subjects and 2,800 trials. Finally, utilizing a convolution-deconvolution network, we propose a new technique towards identifying salient brain regions corresponding to various affective states.
Easy-to-use,Modular and Extendible package of deep-learning based CTR models.DeepFM,DeepInterestNetwork(DIN),DeepInterestEvolutionNetwork(DIEN),DeepCrossNetwork(DCN),AttentionalFactorizationMachine(AFM),Neural Factorization Machine(NFM),AutoInt,Deep Session Interest Network(DSIN)
The Hessian matrix has a number of important applications in a variety of different fields, such as optimzation, image processing and statistics. In this paper we focus on the practical aspects of efficiently computing Hessian matrices in the context of deep learning using the Python scripting language and the TensorFlow library. We define a general feed-forward neural network model and show how to efficiently compute two quantities: the cost function's exact Hessian matrix, and the cost function's approximate Hessian matrix, known as the Outer Product of Gradients (OPG) matrix. Furthermore, as the number of parameters (weights and biases) in deep learning usually is very large, we show how to reduce the quadratic space complexity by an efficient implementation based on approximate eigendecompositions.
Segmenting a chunk of text into words is usually the first step of processing Chinese text, but its necessity has rarely been explored. In this paper, we ask the fundamental question of whether Chinese word segmentation (CWS) is necessary for deep learning-based Chinese Natural Language Processing. We benchmark neural word-based models which rely on word segmentation against neural char-based models which do not involve word segmentation in four end-to-end NLP benchmark tasks: language modeling, machine translation, sentence matching/paraphrase and text classification. Through direct comparisons between these two types of models, we find that char-based models consistently outperform word-based models. Based on these observations, we conduct comprehensive experiments to study why word-based models underperform char-based models in these deep learning-based NLP tasks. We show that it is because word-based models are more vulnerable to data sparsity and the presence of out-of-vocabulary (OOV) words, and thus more prone to overfitting. We hope this paper could encourage researchers in the community to rethink the necessity of word segmentation in deep learning-based Chinese Natural Language Processing. \footnote{Yuxian Meng and Xiaoya Li contributed equally to this paper.}
Tremendous headway has been made in the field of 3D hand pose estimation but the 3D depth cameras are usually inaccessible. We propose a model to recognize American Sign Language alphabet from RGB images. Images for the training were resized and pre-processed before training the Deep Neural Network. The model was trained on a squeezenet architecture to make it capable of running on mobile devices with an accuracy of 83.29%.
Plug-and-play (PnP) is a non-convex framework that integrates modern denoising priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal algorithms. An advantage of PnP is that one can use pre-trained denoisers when there is not sufficient data for end-to-end training. Although PnP has been recently studied extensively with great empirical success, theoretical analysis addressing even the most basic question of convergence has been insufficient. In this paper, we theoretically establish convergence of PnP-FBS and PnP-ADMM, without using diminishing stepsizes, under a certain Lipschitz condition on the denoisers. We then propose real spectral normalization, a technique for training deep learning-based denoisers to satisfy the proposed Lipschitz condition. Finally, we present experimental results validating the theory.
In this letter, we propose a multitask deep learning method for classification of multiple hyperspectral data in a single training. Deep learning models have achieved promising results on hyperspectral image classification, but their performance highly rely on sufficient labeled samples, which are scarce on hyperspectral images. However, samples from multiple data sets might be sufficient to train one deep learning model, thereby improving its performance. To do so, we trained an identical feature extractor for all data, and the extracted features were fed into corresponding Softmax classifiers. Spectral knowledge was introduced to ensure that the shared features were similar across domains. Four hyperspectral data sets were used in the experiments. We achieved higher classification accuracies on three data sets (Pavia University, Pavia Center, and Indian Pines) and competitive results on the Salinas Valley data compared with the baseline. Spectral knowledge was useful to prevent the deep network from overfitting when the data shared similar spectral response. The proposed method tested on two deep CNNs successfully shows its ability to utilize samples from multiple data sets and enhance networks' performance.
Deep learning approaches to cyclone intensity estimationhave recently shown promising results. However, sufferingfrom the extreme scarcity of cyclone data on specific in-tensity, most existing deep learning methods fail to achievesatisfactory performance on cyclone intensity estimation,especially on classes with few instances. To avoid the degra-dation of recognition performance caused by scarce samples,we propose a context-aware CycleGAN which learns the la-tent evolution features from adjacent cyclone intensity andsynthesizes CNN features of classes lacking samples fromunpaired source classes. Specifically, our approach synthe-sizes features conditioned on the learned evolution features,while the extra information is not required. Experimentalresults of several evaluation methods show the effectivenessof our approach, even can predicting unseen classes.
Deep learning based methods have penetrated many image processing problems and become dominant solutions to these problems. A natural question raised here is "Is there any space for conventional methods on these problems?" In this paper, exposure interpolation is taken as an example to answer this question and the answer is "Yes". A framework on fusing conventional and deep learning method is introduced to generate an medium exposure image for two large-exposureratio images. Experimental results indicate that the quality of the medium exposure image is increased significantly through using the deep learning method to refine the interpolated image via the conventional method. The conventional method can be adopted to improve the convergence speed of the deep learning method and to reduce the number of samples which is required by the deep learning method.
There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of $\mathit{embedding}$ code and natural language queries, into real vectors and then using vector distance to approximate semantic correlation between code and the query. Multiple approaches exist for learning these embeddings, including $\mathit{unsupervised}$ techniques, which rely only on a corpus of code examples, and $\mathit{supervised}$ techniques, which use an $\mathit{aligned}$ corpus of paired code and natural language descriptions. The goal of this supervision is to produce embeddings that are more similar for a query and the corresponding desired code snippet. Clearly, there are choices in whether to use supervised techniques at all, and if one does, what sort of network and training to use for supervision. This paper is the first to evaluate these choices systematically. To this end, we assembled implementations of state-of-the-art techniques to run on a common platform, training and evaluation corpora. To explore the design space in network complexity, we also introduced a new design point that is a $\mathit{minimal}$ supervision extension to an existing unsupervised technique. Our evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more sophisticated sequence-based networks for code search; 3. while it is common to use docstrings to carry out supervision, there is a sizeable gap between the effectiveness of docstrings and a more query-appropriate supervision corpus. The evaluation dataset is now available at arXiv:1908.09804
Brain-Computer Interface (BCI) bridges the human's neural world and the outer physical world by decoding individuals' brain signals into commands recognizable by computer devices. Deep learning has lifted the performance of brain-computer interface systems significantly in recent years. In this article, we systematically investigate brain signal types for BCI and related deep learning concepts for brain signal analysis. We then present a comprehensive survey of deep learning techniques used for BCI, by summarizing over 230 contributions most published in the past five years. Finally, we discuss the applied areas, opening challenges, and future directions for deep learning-based BCI.
Deep Learning (DL) has become a crucial technology for Artificial Intelligence (AI). It is a powerful technique to automatically extract high-level features from complex data which can be exploited for applications such as computer vision, natural language processing, cybersecurity, communications, and so on. For the particular case of computer vision, several algorithms like object detection in real time videos have been proposed and they work well on Desktop GPUs and distributed computing platforms. However these algorithms are still heavy for mobile and embedded visual applications. The rapid spreading of smart portable devices and the emerging 5G network are introducing new smart multimedia applications in mobile environments. As a consequence, the possibility of implementing deep neural networks to mobile environments has attracted a lot of researchers. This paper presents emerging deep learning acceleration techniques that can enable the delivery of real time visual recognition into the hands of end users, anytime and anywhere.
The increasingly fast development cycle for online course contents, along with the diverse student demographics in each online classroom, make real-time student outcomes prediction an interesting topic for both industrial research and practical needs. In this paper, we tackle the problem of real-time student performance prediction in an on-going course using a domain adaptation framework. This framework is a system trained on labeled student outcome data from previous coursework but is meant to be deployed on another course. In particular, we introduce a GritNet architecture, and develop an unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any student outcome label. Our results for real Udacity student graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but also enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging.
Typically, deep learning architectures are handcrafted for their respective learning problem. As an alternative, neural architecture search (NAS) has been proposed where the architecture's structure is learned in an additional optimization step. For the medical imaging domain, this approach is very promising as there are diverse problems and imaging modalities that require architecture design. However, NAS is very time-consuming and medical learning problems often involve high-dimensional data with high computational requirements. We propose an efficient approach for NAS in the context of medical, image-based deep learning problems by searching for architectures on low-dimensional data which are subsequently transferred to high-dimensional data. For OCT-based layer segmentation, we demonstrate that a search on 1D data reduces search time by 87.5% compared to a search on 2D data while the final 2D models achieve similar performance.
Ocular pathology detection from fundus images presents an important challenge on health care. In fact, each pathology has different severity stages that may be deduced by verifying the existence of specific lesions. Each lesion is characterized by morphological features. Moreover, several lesions of different pathologies have similar features. We note that patient may be affected simultaneously by several pathologies. Consequently, the ocular pathology detection presents a multi-class classification with a complex resolution principle. Several detection methods of ocular pathologies from fundus images have been proposed. The methods based on deep learning are distinguished by higher performance detection, due to their capability to configure the network with respect to the detection objective. This work proposes a survey of ocular pathology detection methods based on deep learning. First, we study the existing methods either for lesion segmentation or pathology classification. Afterwards, we extract the principle steps of processing and we analyze the proposed neural network structures. Subsequently, we identify the hardware and software environment required to employ the deep learning architecture. Thereafter, we investigate about the experimentation principles involved to evaluate the methods and the databases used either for training and testing phases. The detection performance ratios and execution times are also reported and discussed.
Deep learning is one of the fastest growing technologies in computer science with a plethora of applications. But this unprecedented growth has so far been limited to the consumption of deep learning experts. The primary challenge being a steep learning curve for learning the programming libraries and the lack of intuitive systems enabling non-experts to consume deep learning. Towards this goal, we study the effectiveness of a no-code paradigm for designing deep learning models. Particularly, a visual drag-and-drop interface is found more efficient when compared with the traditional programming and alternative visual programming paradigms. We conduct user studies of different expertise levels to measure the entry level barrier and the developer load across different programming paradigms. We obtain a System Usability Scale (SUS) of 90 and a NASA Task Load index (TLX) score of 21 for the proposed visual programming compared to 68 and 52, respectively, for the traditional programming methods.
In the field of sequential recommendation, deep learning (DL)-based methods have received a lot of attention in the past few years and surpassed traditional models such as Markov chain-based and factorization-based ones. However, there is little systematic study on DL-based methods, especially regarding to how to design an effective DL model for sequential recommendation. In this view, this survey focuses on DL-based sequential recommender systems by taking the aforementioned issues into consideration. Specifically,we illustrate the concept of sequential recommendation, propose a categorization of existing algorithms in terms of three types of behavioral sequence, summarize the key factors affecting the performance of DL-based models, and conduct corresponding evaluations to demonstrate the effects of these factors. We conclude this survey by systematically outlining future directions and challenges in this field.
Recommendation systems have become ubiquitous in today's online world and are an integral part of practically every e-commerce platform. While traditional recommender systems use customer history, this approach is not feasible in 'cold start' scenarios. Such scenarios include the need to produce recommendations for new or unregistered users and the introduction of new items. In this study, we present the Purchase Intent Session-bAsed (PISA) algorithm, a content-based algorithm for predicting the purchase intent for cold start session-based scenarios. Our approach employs deep learning techniques both for modeling the content and purchase intent prediction. Our experiments show that PISA outperforms a well-known deep learning baseline when new items are introduced. In addition, while content-based approaches often fail to perform well in highly imbalanced datasets, our approach successfully handles such cases. Finally, our experiments show that combining PISA with the baseline in non-cold start scenarios further improves performance.
The growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of automated methods for neural architecture search. The choice of the network architecture has proven to be critical, and many advances in deep learning spring from its immediate improvements. However, deep learning techniques are computationally intensive and their application requires a high level of domain knowledge. Therefore, even partial automation of this process helps to make deep learning more accessible to both researchers and practitioners. With this survey, we provide a formalism which unifies and categorizes the landscape of existing methods along with a detailed analysis that compares and contrasts the different approaches. We achieve this via a comprehensive discussion of the commonly adopted architecture search spaces and architecture optimization algorithms based on principles of reinforcement learning and evolutionary algorithms along with approaches that incorporate surrogate and one-shot models. Additionally, we address the new research directions which include constrained and multi-objective architecture search as well as automated data augmentation, optimizer and activation function search.
Artificial Intelligence (AI), defined in its most simple form, is a technological tool that makes machines intelligent. Since learning is at the core of intelligence, machine learning poses itself as a core sub-field of AI. Then there comes a subclass of machine learning, known as deep learning, to address the limitations of their predecessors. AI has generally acquired its prominence over the past few years due to its considerable progress in various fields. AI has vastly invaded the realm of research. This has led physicists to attentively direct their research towards implementing AI tools. Their central aim has been to gain better understanding and enrich their intuition. This review article is meant to supplement the previously presented efforts to bridge the gap between AI and physics, and take a serious step forward to filter out the "Babelian" clashes brought about from such gabs. This necessitates first to have fundamental knowledge about common AI tools. To this end, the review's primary focus shall be on deep learning models called artificial neural networks. They are deep learning models which train themselves through different learning processes. It discusses also the concept of Markov decision processes. Finally, shortcut to the main goal, the review thoroughly examines how these neural networks are capable to construct a physical theory describing some observations without applying any previous physical knowledge.