We present a self-supervised deep multi-task learning framework for electrocardiogram (ECG) -based emotion recognition. The proposed framework consists of two stages of learning a) learning ECG representations and b) learning to classify emotions. ECG representations are learned by a signal transformation recognition network. The network learns high-level abstract representations from unlabeled ECG data. Six different signal transformations are applied to the ECG signals, and transformation recognition is performed as pretext tasks. Training the model on pretext tasks helps our network learn spatiotemporal representations that generalize well across different datasets and different emotion categories. We transfer the weights of the self-supervised network to an emotion recognition network, where the convolutional layers are kept frozen and the dense layers are trained with labelled ECG data. We show that our proposed method considerably improves the performance compared to a network trained using fully-supervised learning. New state-of-the-art results are set in classification of arousal, valence, affective states, and stress for the four utilized datasets. Extensive experiments are performed, providing interesting insights into the impact of using a multi-task self-supervised structure instead of a single-task model, as well as the optimum level of difficulty required for the pretext self-supervised tasks.

The ubiquitous deployment of monitoring devices in urban flow monitoring systems induces a significant cost for maintenance and operation. A technique is required to reduce the number of deployed devices, while preventing the degeneration of data accuracy and granularity. In this paper, we present an approach for inferring the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations. This task exhibits two challenges: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a model entitled UrbanFM which consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs that uses a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influence of different external factors. This structure provides outstanding effectiveness and efficiency for small scale upsampling. However, the single-pass upsampling used by UrbanFM is insufficient at higher upscaling rates. Therefore, we further present UrbanPy, a cascading model for progressive inference of fine-grained urban flows by decomposing the original tasks into multiple subtasks. Compared to UrbanFM, such an enhanced structure demonstrates favorable performance for larger-scale inference tasks.

Topology optimization by distributing materials in a domain requires stochastic optimizers to solve highly complicated problems. However, solving such problems requires millions of finite element calculations with hundreds of design variables or more involved , whose computational cost is huge and often unacceptable. To speed up computation, here we report a method to integrate deep learning into stochastic optimization algorithm. A Deep Neural Network (DNN) learns and substitutes the objective function by forming a loop with Generative Simulated Annealing (GSA). In each iteration, GSA uses DNN to evaluate the objective function to obtain an optimized solution, based on which new training data are generated; thus, DNN enhances its accuracy and GSA could accordingly improve its solution in next iteration until convergence. Our algorithm was tested by compliance minimization problems and reduced computational time by over two orders of magnitude. This approach sheds light on solving large multi-dimensional optimization problems.

Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epochs and there is a gap between large-batch deep learning optimization heuristics and theoretical underpinnings. In this paper, we propose a novel Complete Layer-wise Adaptive Rate Scaling (CLARS) algorithm for large-batch training. We also analyze the convergence rate of the proposed method by introducing a new fine-grained analysis of gradient-based methods. Based on our analysis, we bridge the gap and illustrate the theoretical insights for three popular large-batch training techniques, including linear learning rate scaling, gradual warmup, and layer-wise adaptive rate scaling. Extensive experiments demonstrate that the proposed algorithm outperforms gradual warmup technique by a large margin and defeats the convergence of the state-of-the-art large-batch optimizer in training advanced deep neural networks (ResNet, DenseNet, MobileNet) on ImageNet dataset.

Maps of brain microarchitecture are important for understanding neurological function and behavior, including alterations caused by chronic conditions such as neurodegenerative disease. Techniques such as knife-edge scanning microscopy (KESM) provide the potential for whole organ imaging at sub-cellular resolution. However, multi-terabyte data sizes make manual annotation impractical and automatic segmentation challenging. Densely packed cells combined with interconnected microvascular networks are a challenge for current segmentation algorithms. The massive size of high-throughput microscopy data necessitates fast and largely unsupervised algorithms. In this paper, we investigate a fully-convolutional, deep, and densely-connected encoder-decoder for pixel-wise semantic segmentation. The excessive memory complexity often encountered with deep and dense networks is mitigated using skip connections, resulting in fewer parameters and enabling a significant performance increase over prior architectures. The proposed network provides superior performance for semantic segmentation problems applied to open-source benchmarks. We finally demonstrate our network for cellular and microvascular segmentation, enabling quantitative metrics for organ-scale neurovascular analysis.

We study the role of depth in training randomly initialized overparameterized neural networks. We give the first general result showing that depth improves trainability of neural networks by improving the {\em conditioning} of certain kernel matrices of the input data. This result holds for arbitrary non-linear activation functions, and we provide a characterization of the improvement in conditioning as a function of the degree of non-linearity and the depth of the network. We provide versions of the result that hold for training just the top layer of the neural network, as well as for training all layers, via the neural tangent kernel. As applications of these general results, we provide a generalization of the results of Das et al. (2019) showing that learnability of deep random neural networks with arbitrary non-linear activations (under mild assumptions) degrades exponentially with depth. Additionally, we show how benign overfitting can occur in deep neural networks via the results of Bartlett et al. (2019b).

Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However the expensive numerous updates in parallel limited the approach to small tabular cases so far. To tackle this problem we propose to use convolutional network architectures to generate Q-values and updates for a large number of goals at once. We demonstrate the accuracy and generalization qualities of the proposed method on randomly generated mazes and Sokoban puzzles. In the case of on-screen goal coordinates the resulting mapping from frames to distance-maps directly informs the agent about which places are reachable and in how many steps. As an example of application we show that replacing the random actions in epsilon-greedy exploration by several actions towards feasible goals generates better exploratory trajectories on Montezuma's Revenge and Super Mario All-Stars games.

Massive Open Online Courses (MOOCs) have become popular platforms for online learning. While MOOCs enable students to study at their own pace, this flexibility makes it easy for students to drop out of class. In this paper, our goal is to predict if a learner is going to drop out within the next week, given clickstream data for the current week. To this end, we present a multi-layer representation learning solution based on branch and bound (BB) algorithm, which learns from low-level clickstreams in an unsupervised manner, produces interpretable results, and avoids manual feature engineering. In experiments on Coursera data, we show that our model learns a representation that allows a simple model to perform similarly well to more complex, task-specific models, and how the BB algorithm enables interpretable results. In our analysis of the observed limitations, we discuss promising future directions.

Deep learning models are being deployed in many mobile intelligent applications. End-side services, such as intelligent personal assistants, autonomous cars, and smart home services often employ either simple local models on the mobile or complex remote models on the cloud. However, recent studies have shown that partitioning the DNN computations between the mobile and cloud can increase the latency and energy efficiencies. In this paper, we propose an efficient, adaptive, and practical engine, JointDNN, for collaborative computation between a mobile device and cloud for DNNs in both inference and training phase. JointDNN not only provides an energy and performance efficient method of querying DNNs for the mobile side but also benefits the cloud server by reducing the amount of its workload and communications compared to the cloud-only approach. Given the DNN architecture, we investigate the efficiency of processing some layers on the mobile device and some layers on the cloud server. We provide optimization formulations at layer granularity for forward- and backward-propagations in DNNs, which can adapt to mobile battery limitations and cloud server load constraints and quality of service. JointDNN achieves up to 18 and 32 times reductions on the latency and mobile energy consumption of querying DNNs compared to the status-quo approaches, respectively.

State-of-the-art performance and low system complexity has made deep-learning an increasingly attractive solution for big data analytics. However, limiting assumptions of end-to-end learning regimes hinder the use of neural networks on large application-grade datasets. This work addresses the assumption that output class-labels are defined for all classes in the domain. The amount of data collected by modern-day sensors span over an incomprehensible range of potential classes. Therefore, we propose a new learning regime where only some, but not all, classes of the training data are of interest to the classification system. The semi-supervised learning scenario in big data requires the assumption of a partial class mismatch between labelled and unlabelled training data. With classification systems required to classify source classes indicated by labelled samples while separating novel classes indicated by unlabelled samples, we find ourselves in an open-set case (vs closed set with only source classes). However, introducing samples from novel classes into the training set indicates a more relaxed open-set case. As such, our proposed regime of \textit{quasi-open set semi-supervised learning} is introduced. We propose a suitable method to train under quasi-open set semi-supervised learning that makes use of Wasserstein generative adversarial networks (WGANs). A trained classification certainty estimation within the discriminator (or critic) network is used to enable a reject option for the classifier. By placing a threshold on this certainty estimation, the reject option accepts classifications of source classes and rejects novel classes. Big data end-to-end training is promoted by developing models that recognize input samples do not necessarily belong to output labels. We believe this essential for big data analytics, and urge more work under quasi-open set semi-supervised learning.