In this paper, we propose a deep learning based assistive system to improve the environment perception experience of visually impaired (VI). The system is composed of a wearable terminal equipped with an RGBD camera and an earphone, a powerful processor mainly for deep learning inferences and a smart phone for touch-based interaction. A data-driven learning approach is proposed to predict safe and reliable walkable instructions using RGBD data and the established semantic map. This map is also used to help VI understand their 3D surrounding objects and layout through well-designed touchscreen interactions. The quantitative and qualitative experimental results show that our learning based obstacle avoidance approach achieves excellent results in both indoor and outdoor datasets with low-lying obstacles. Meanwhile, user studies have also been carried out in various scenarios and showed the improvement of VI's environment perception experience with our system.
Physicians use biopsies to distinguish between different but histologically similar enteropathies. The range of syndromes and pathologies that could cause different gastrointestinal conditions makes this a difficult problem. Recently, deep learning has been used successfully in helping diagnose cancerous tissues in histopathological images. These successes motivated the research presented in this paper, which describes a deep learning approach that distinguishes between Celiac Disease (CD) and Environmental Enteropathy (EE) and normal tissue from digitized duodenal biopsies. Experimental results show accuracies of over 90% for this approach. We also look into interpreting the neural network model using Gradient-weighted Class Activation Mappings and filter activations on input images to understand the visual explanations for the decisions made by the model.
The internet of things (IoT) is transforming major industries including but not limited to healthcare, agriculture, finance, energy, and transportation. IoT platforms are continually improving with innovations such as the amalgamation of software-defined networks (SDN) and network function virtualization (NFV) in the edge-cloud interplay. Deep learning (DL) is becoming popular due to its remarkable accuracy when trained with a massive amount of data, such as generated by IoT. However, DL algorithms tend to leak privacy when trained on highly sensitive crowd-sourced data such as medical data. Existing privacy-preserving DL algorithms rely on the traditional server-centric approaches requiring high processing powers. We propose a new local differentially private (LDP) algorithm named LATENT that redesigns the training process. LATENT enables a data owner to add a randomization layer before data leave the data owners' devices and reach a potentially untrusted machine learning service. This feature is achieved by splitting the architecture of a convolutional neural network (CNN) into three layers: (1) convolutional module, (2) randomization module, and (3) fully connected module. Hence, the randomization module can operate as an NFV privacy preservation service in an SDN-controlled NFV, making LATENT more practical for IoT-driven cloud-based environments compared to existing approaches. The randomization module employs a newly proposed LDP protocol named utility enhancing randomization, which allows LATENT to maintain high utility compared to existing LDP protocols. Our experimental evaluation of LATENT on convolutional deep neural networks demonstrates excellent accuracy (e.g. 91%- 96%) with high model quality even under low privacy budgets (e.g. $\varepsilon=0.5$).
Although the currently popular deep learning networks achieve unprecedented performance on some tasks, the human brain still has a monopoly on general intelligence. Motivated by this and biological implausibility of deep learning networks, we developed a family of biologically plausible artificial neural networks (NNs) for unsupervised learning. Our approach is based on optimizing principled objective functions containing a term that matches the pairwise similarity of outputs to the similarity of inputs, hence the name - similarity-based. Gradient-based online optimization of such similarity-based objective functions can be implemented by NNs with biologically plausible local learning rules. Similarity-based cost functions and associated NNs solve unsupervised learning tasks such as linear dimensionality reduction, sparse and/or nonnegative feature extraction, blind nonnegative source separation, clustering and manifold learning.
In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method which leverages on moving a 2D camera by means of a robot, proving precise camera tracking, and an augmented reality pen to define initial object bounding box, to create large labeled datasets with minimal human intervention. By removing the burden of generating annotated data from humans, we make the Deep Learning technique applied to computer vision, that typically requires very large datasets, truly automated and reliable. With the ARS pipeline, we created effortlessly two novel datasets, one on electromechanical components (industrial scenario) and one on fruits (daily-living scenario), and trained robustly two state-of-the-art object detectors, based on convolutional neural networks, such as YOLO and SSD. With respect to the conventional manual annotation of 1000 frames that takes us slightly more than 10 hours, the proposed approach based on ARS allows annotating 9 sequences of about 35000 frames in less than one hour, with a gain factor of about 450. Moreover, both the precision and recall of object detection is increased by about 15\% with respect to manual labeling. All our software is available as a ROS package in a public repository alongside the novel annotated datasets.
The past, present and future of deep learning is presented in this work. Given this landscape & roadmap, we predict that deep cortical learning will be the convergence of deep learning & cortical learning which builds an artificial cortical column ultimately.
In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network models for training as well as comprehensive deployment tools for production. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. We demonstrate the reliable performance with DELTA on several natural language processing and speech tasks, including text classification, named entity recognition, natural language inference, speech recognition, speaker verification, etc. DELTA has been used for developing several state-of-the-art algorithms for publications and delivering real production to serve millions of users.
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high performance can be explained by efficient knowledge representation of deep learning models. While many methods have been proposed to learn more efficient representation, knowledge distillation from pretrained deep networks suggest that we can use more information from the soft target probability to train other neural networks. In this paper, we propose a new knowledge distillation method self-knowledge distillation, based on the soft target probabilities of the training model itself, where multimode information is distilled from the word embedding space right below the softmax layer. Due to the time complexity, our method approximates the soft target probabilities. In experiments, we applied the proposed method to two different and fundamental NLP tasks: language model and neural machine translation. The experiment results show that our proposed method improves performance on the tasks.
In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets). The ASNet is a neural network architecture that exploits the relational structure of (P)PDDL planning problems to learn a common set of weights that can be applied to any problem in a domain. By mimicking the actions chosen by a traditional, non-learning planner on a handful of small problems in a domain, ASNets are able to learn a generalised reactive policy that can quickly solve much larger instances from the domain. This work extends the ASNet architecture to make it more expressive, while still remaining invariant to a range of symmetries that exist in PPDDL problems. We also present a thorough experimental evaluation of ASNets, including a comparison with heuristic search planners on seven probabilistic and deterministic domains, an extended evaluation on over 18,000 Blocksworld instances, and an ablation study. Finally, we show that sparsity-inducing regularisation can produce ASNets that are compact enough for humans to understand, yielding insights into how the structure of ASNets allows them to generalise across a domain.
With the significant growth of advanced high-frequency power converters, on-line monitoring and active reliability assessment of power electronic devices are extremely crucial. This article presents a transformative approach, named Deep Learning Reliability Awareness of Converters at the Edge (Deep RACE), for real-time reliability modeling and prediction of high-frequency MOSFET power electronic converters. Deep RACE offers a holistic solution which comprises algorithm advances, and full system integration (from the cloud down to the edge node) to create a near real-time reliability awareness. On the algorithm side, this paper proposes a deep learning algorithmic solution based on stacked LSTM for collective reliability training and inference across collective MOSFET converters based on device resistance changes. Deep RACE also proposes an integrative edge-to-cloud solution to offer a scalable decentralized devices-specific reliability monitoring, awareness, and modeling. The MOSFET convertors are IoT devices which have been empowered with edge real-time deep learning processing capabilities. The proposed Deep RACE solution has been prototyped and implemented through learning from MOSFET data set provided by NASA. Our experimental results show an average miss prediction of $8.9\%$ over five different devices which is a much higher accuracy compared to well-known classical approaches (Kalman Filter, and Particle Filter). Deep RACE only requires $26ms$ processing time and $1.87W$ computing power on Edge IoT device.
Nowadays many financial derivatives, such as American or Bermudan options, are of early exercise type. Often the pricing of early exercise options gives rise to high-dimensional optimal stopping problems, since the dimension corresponds to the number of underlying assets. High-dimensional optimal stopping problems are, however, notoriously difficult to solve due to the well-known curse of dimensionality. In this work, we propose an algorithm for solving such problems, which is based on deep learning and computes, in the context of early exercise option pricing, both approximations of an optimal exercise strategy and the price of the considered option. The proposed algorithm can also be applied to optimal stopping problems that arise in other areas where the underlying stochastic process can be efficiently simulated. We present numerical results for a large number of example problems, which include the pricing of many high-dimensional American and Bermudan options, such as Bermudan max-call options in up to 5000 dimensions. Most of the obtained results are compared to reference values computed by exploiting the specific problem design or, where available, to reference values from the literature. These numerical results suggest that the proposed algorithm is highly effective in the case of many underlyings, in terms of both accuracy and speed.
The purpose of this work is to develop a deep learning-based method for knee menisci segmentation in 3D ultrashort echo time (UTE) cones magnetic resonance (MR) imaging, and to automatically determine MR relaxation times, namely the T1, T1$\rho$, and T2* parameters, which can be used to assess knee osteoarthritis (OA). Whole knee joint imaging was performed using 3D UTE cones sequences to collect data from 61 human subjects. Regions of interest (ROIs) were outlined by two experienced radiologists based on subtracted T1$\rho$-weighted MR images. Transfer learning was applied to develop 2D attention U-Net convolutional neural networks for the menisci segmentation based on each radiologist's ROIs separately. Dice scores were calculated to assess segmentation performance. Next, the T1, T1$\rho$, T2* relaxations, and ROI areas were determined for the manual and automatic segmentations, then compared.The models developed using ROIs provided by two radiologists achieved high Dice scores of 0.860 and 0.833, while the radiologists' manual segmentations achieved a Dice score of 0.820. Linear correlation coefficients for the T1, T1$\rho$, and T2* relaxations calculated using the automatic and manual segmentations ranged between 0.90 and 0.97, and there were no associated differences between the estimated average meniscal relaxation parameters. The deep learning models achieved segmentation performance equivalent to the inter-observer variability of two radiologists. The proposed deep learning-based approach can be used to efficiently generate automatic segmentations and determine meniscal relaxations times. The method has the potential to help radiologists with the assessment of meniscal diseases, such as OA.
We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks. The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates exploding and vanishing gradients, resulting in the ability to learn very deep networks without skip connections. There is no requirement for symmetric feedback or update locking. We find that the HSIC bottleneck provides performance on MNIST/FashionMNIST/CIFAR10 classification comparable to backpropagation with a cross-entropy target, even when the system is not encouraged to make the output resemble the classification labels. Appending a single layer trained with SGD (without backpropagation) to reformat the information further improves performance.
Recent successes in language modeling, notably with deep learning methods, coincide with a shift from probabilistic to weighted representations. We raise here the question of the importance of this evolution, in the light of the practical limitations of a classical and simple probabilistic modeling approach for the classification of protein sequences and in relation to the need for principled methods to learn non-probabilistic models.
The success of deep learning has been witnessed as a promising technique for computer-aided biomedical image analysis, due to end-to-end learning framework and availability of large-scale labelled samples. However, in many cases of biomedical image analysis, deep learning techniques suffer from the small sample learning (SSL) dilemma caused mainly by lack of annotations. To be more practical for biomedical image analysis, in this paper we survey the key SSL techniques that help relieve the suffering of deep learning by combining with the development of related techniques in computer vision applications. In order to accelerate the clinical usage of biomedical image analysis based on deep learning techniques, we intentionally expand this survey to include the explanation methods for deep models that are important to clinical decision making. We survey the key SSL techniques by dividing them into five categories: (1) explanation techniques, (2) weakly supervised learning techniques, (3) transfer learning techniques, (4) active learning techniques, and (5) miscellaneous techniques involving data augmentation, domain knowledge, traditional shallow methods and attention mechanism. These key techniques are expected to effectively support the application of deep learning in clinical biomedical image analysis, and furtherly improve the analysis performance, especially when large-scale annotated samples are not available. We bulid demos at https://github.com/PengyiZhang/MIADeepSSL.
Deep learning models require the configuration of many layers and parameters in order to get good results. However, there are currently few systematic guidelines for how to configure a successful model. This means model builders often have to experiment with different configurations by manually programming different architectures (which is tedious and time consuming) or rely on purely automated approaches to generate and train the architectures (which is expensive). In this paper, we present Rapid Exploration of Model Architectures and Parameters, or REMAP, a visual analytics tool that allows a model builder to discover a deep learning model quickly via exploration and rapid experimentation of neural network architectures. In REMAP, the user explores the large and complex parameter space for neural network architectures using a combination of global inspection and local experimentation. Through a visual overview of a set of models, the user identifies interesting clusters of architectures. Based on their findings, the user can run ablation and variation experiments to identify the effects of adding, removing, or replacing layers in a given architecture and generate new models accordingly. They can also handcraft new models using a simple graphical interface. As a result, a model builder can build deep learning models quickly, efficiently, and without manual programming. We inform the design of REMAP through a design study with four deep learning model builders. Through a use case, we demonstrate that REMAP allows users to discover performant neural network architectures efficiently using visual exploration and user-defined semi-automated searches through the model space.
Accurate day-ahead individual residential load forecasting is of great importance to various applications of smart grid on day-ahead market. Deep learning, as a powerful machine learning technology, has shown great advantages and promising application in load forecasting tasks. However, deep learning is a computationally-hungry method, and requires high costs (e.g., time, energy and CO2 emission) to train a deep learning model, which aggravates the energy crisis and incurs a substantial burden to the environment. As a consequence, the deep learning methods are difficult to be popularized and applied in the real smart grid environment. In this paper, we propose a low training cost model based on convolutional neural network, namely LoadCNN, for next-day load forecasting of individual resident with reduced training cost. The experiments show that the training time of LoadCNN is only approximately 1/54 of the one of other state-of-the-art models, and energy consumption and CO2 emissions are only approximate 1/45 of those of other state-of-the-art models based on the same indicators. Meanwhile, the prediction accuracy of our model is equal to that of current state-of-the-art models, making LoadCNN the first load forecasting model simultaneously achieving high prediction accuracy and low training costs. LoadCNN is an efficient green model that is able to be quickly, cost-effectively and environmentally-friendly deployed in a realistic smart grid environment.
Software frameworks for neural networks play a key role in the development and application of deep learning methods. In this paper, we introduce the Chainer framework, which intends to provide a flexible, intuitive, and high performance means of implementing the full range of deep learning models needed by researchers and practitioners. Chainer provides acceleration using Graphics Processing Units with a familiar NumPy-like API through CuPy, supports general and dynamic models in Python through Define-by-Run, and also provides add-on packages for state-of-the-art computer vision models as well as distributed training.
A current clinical challenge is identifying limb girdle muscular dystrophy 2I(LGMD2I)tissue changes in the thighs, in particular, separating fat, fat-infiltrated muscle, and muscle tissue. Deep learning algorithms have the ability to learn different features by using the inherent tissue contrasts from multiparametric magnetic resonance imaging (mpMRI). To that end, we developed a novel multiparametric deep learning network (MPDL) tissue signature model based on mpMRI and applied it to LGMD2I. We demonstrate a new tissue signature model of muscular dystrophy with the MPDL algorithm segments different tissue types with excellent results.
Drug-Drug Interactions (DDIs) Extraction refers to the efforts to generate hand-made or automatic tools to extract embedded information from text and literature in the biomedical domain. Because of restrictions in hand-made efforts and their lower speed, Machine-Learning, or Deep-Learning approaches have become more popular for extracting DDIs. In this study, we propose a novel and generic Deep-Learning model which wraps Hierarchical Bidirectional LSTMs with two Attention Mechanisms that outperforms state-of-the-art models for DDIs Extraction, based on the DDIExtraction-2013 corpora. This model has obtained the macro F1-score of 0.785, and the precision of 0.80.