To solve the problem of the overwhelming size of Deep Neural Networks (DNN) several compression schemes have been proposed, one of them is teacher-student. Teacher-student tries to transfer knowledge from a complex teacher network to a simple student network. In this paper, we propose a novel method called a teacher-class network consisting of a single teacher and multiple student networks (i.e. class of students). Instead of transferring knowledge to one student only, the proposed method transfers a chunk of knowledge about the entire solution to each student. Our students are not trained for problem-specific logits, they are trained to mimic knowledge (dense representation) learned by the teacher network. Thus unlike the logits-based single student approach, the combined knowledge learned by the class of students can be used to solve other problems as well. These students can be designed to satisfy a given budget, e.g. for comparative purposes we kept the collective parameters of all the students less than or equivalent to that of a single student in the teacher-student approach . These small student networks are trained independently, making it possible to train and deploy models on memory deficient devices as well as on parallel processing systems such as data centers. The proposed teacher-class architecture is evaluated on several benchmark datasets including MNIST, FashionMNIST, IMDB Movie Reviews and CAMVid on multiple tasks including classification, sentiment classification and segmentation. Our approach outperforms the state-of-the-art single student approach in terms of accuracy as well as computational cost and in many cases it achieves an accuracy equivalent to the teacher network while having 10-30 times fewer parameters.

As machine learning for images becomes democratized in the Software 2.0 era, one of the serious bottlenecks is securing enough labeled data for training. This problem is especially critical in a manufacturing setting where smart factories rely on machine learning for product quality control by analyzing industrial images. Such images are typically large and may only need to be partially analyzed where only a small portion is problematic (e.g., identifying defects on a surface). Since manual labeling these images is expensive, weak supervision is an attractive alternative where the idea is to generate weak labels that are not perfect, but can be produced at scale. Data programming is a recent paradigm in this category where it uses human knowledge in the form of labeling functions and combines them into a generative model. Data programming has been successful in applications based on text or structured data and can also be applied to images usually if one can find a way to convert them into structured data. In this work, we expand the horizon of data programming by directly applying it to images without this conversion, which is a common scenario for industrial applications. We propose Inspector Gadget, an image labeling system that combines crowdsourcing, data augmentation, and data programming to produce weak labels at scale for image classification. We perform experiments on real industrial image datasets and show that Inspector Gadget obtains better accuracy than state-of-the-art techniques: Snuba, GOGGLES, and self-learning baselines using convolutional neural networks (CNNs) without pre-training.

In deep learning tasks, the learning rate determines the update step size in each iteration, which plays a critical role in gradient-based optimization. However, the determination of the appropriate learning rate in practice typically replies on subjective judgement. In this work, we propose a novel optimization method based on local quadratic approximation (LQA). In each update step, given the gradient direction, we locally approximate the loss function by a standard quadratic function of the learning rate. Then, we propose an approximation step to obtain a nearly optimal learning rate in a computationally efficient way. The proposed LQA method has three important features. First, the learning rate is automatically determined in each update step. Second, it is dynamically adjusted according to the current loss function value and the parameter estimates. Third, with the gradient direction fixed, the proposed method leads to nearly the greatest reduction in terms of the loss function. Extensive experiments have been conducted to prove the strengths of the proposed LQA method.

A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These methods are mainly based on visualizing the important input features taken into account by the network to build a decision. However these techniques, let us cite LIME, SHAP, Grad-CAM, or TDS, require extra effort to interpret the visualization with respect to expert knowledge. In this paper, we propose a novel approach to inspect the hidden layers of a fitted CNN in order to extract interpretable linguistic objects from texts exploiting classification process. In particular, we detail a weighted extension of the Text Deconvolution Saliency (wTDS) measure which can be used to highlight the relevant features used by the CNN to perform the classification task. We empirically demonstrate the efficiency of our approach on corpora from two different languages: English and French. On all datasets, wTDS automatically encodes complex linguistic objects based on co-occurrences and possibly on grammatical and syntax analysis.

Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, convolutional neural networks are mainly used as a frame-level feature extractor, and speaker embeddings are extracted from the last layer of the feature extractor. Multi-scale aggregation (MSA), which utilizes multi-scale features from different layers of the feature extractor, has recently been introduced into the approach and has shown improved performance for both short and long utterances. This paper improves the MSA by using a feature pyramid module, which enhances speaker-discriminative information of features at multiple layers via a top-down pathway and lateral connections. We extract speaker embeddings using the enhanced features that contain rich speaker information at different resolutions. Experiments on the VoxCeleb dataset show that the proposed module improves previous MSA methods with a smaller number of parameters, providing better performance than state-of-the-art approaches.

In this paper, we propose a deep learning framework, TSception, for emotion detection from electroencephalogram (EEG). TSception consists of temporal and spatial convolutional layers, which learn discriminative representations in the time and channel domains simultaneously. The temporal learner consists of multi-scale 1D convolutional kernels whose lengths are related to the sampling rate of the EEG signal, which learns multiple temporal and frequency representations. The spatial learner takes advantage of the asymmetry property of emotion responses at the frontal brain area to learn the discriminative representations from the left and right hemispheres of the brain. In our study, a system is designed to study the emotional arousal in an immersive virtual reality (VR) environment. EEG data were collected from 18 healthy subjects using this system to evaluate the performance of the proposed deep learning network for the classification of low and high emotional arousal states. The proposed method is compared with SVM, EEGNet, and LSTM. TSception achieves a high classification accuracy of 86.03%, which outperforms the prior methods significantly (p<0.05). The code is available at https://github.com/deepBrains/TSception

Compressed sensing is applied to scanning transmission electron microscopy to decrease electron dose and scan time. However, established methods use static sampling strategies that do not adapt to samples. We have extended recurrent deterministic policy gradients to train deep LSTMs and differentiable neural computers to adaptively sample scan path segments. Recurrent agents cooperate with a convolutional generator to complete partial scans. We show that our approach outperforms established algorithms based on spiral scans, and we expect our results to be generalizable to other scan systems.

Budgeted pruning is the problem of pruning under resource constraints. In budgeted pruning, how to distribute the resources across layers (i.e., sparsity allocation) is the key problem. Traditional methods solve it by discretely searching for the layer-wise pruning ratios, which lacks efficiency. In this paper, we propose Differentiable Sparsity Allocation (DSA), an efficient end-to-end budgeted pruning flow. Utilizing a novel differentiable pruning process, DSA finds the layer-wise pruning ratios with gradient-based optimization. It allocates sparsity in continuous space, which is more efficient than methods based on discrete evaluation and search. Furthermore, DSA could work in a pruning-from-scratch manner, whereas traditional budgeted pruning methods are applied to pre-trained models. Experimental results on CIFAR-10 and ImageNet show that DSA could achieve superior performance than current iterative budgeted pruning methods, and shorten the time cost of the overall pruning process by at least 1.5x in the meantime.

Inability to test at scale has become Achille's heel in humanity's ongoing war against COVID-19 pandemic. An agile, scalable and cost-effective testing, deployable at a global scale, can act as a game changer in this war. To address this challenge, building on the promising results of our prior work on cough-based diagnosis of a motley of respiratory diseases, we develop an Artificial Intelligence (AI)-based test for COVID-19 preliminary diagnosis. The test is deployable at scale through a mobile app named AI4COVID-19. The AI4COVID-19 app requires 2-second cough recordings of the subject. By analyzing the cough samples through an AI engine running in the cloud, the app returns a preliminary diagnosis within a minute. Unfortunately, cough is common symptom of over two dozen non-COVID-19 related medical conditions. This makes the COVID-19 diagnosis from cough alone an extremely challenging problem. We solve this problem by developing a novel multi-pronged mediator centered risk-averse AI architecture that minimizes misdiagnosis. At the time of writing, our AI engine can distinguish between COVID-19 patient coughs and several types of non-COVID-19 coughs with over 90% accuracy. AI4COVID-19's performance is likely to improve as more and better data becomes available. This paper presents a proof of concept to encourage controlled clinical trials and serves as a call for labeled cough data. AI4COVID-19 is not designed to compete with clinical testing. Instead, it offers a complementing tele-testing tool deployable anytime, anywhere, by anyone, so clinical-testing and treatment can be channeled to those who need it the most, thereby saving more lives.

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In particular, we distill the predictive distribution between different samples of the same label during training. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network (i.e., a self-knowledge distillation) by forcing it to produce more meaningful and consistent predictions in a class-wise manner. Consequently, it mitigates overconfident predictions and reduces intra-class variations. Our experimental results on various image classification tasks demonstrate that the simple yet powerful method can significantly improve not only the generalization ability but also the calibration performance of modern convolutional neural networks.