Deep learning is a subset of a broader family of machine learning methods based on learning data representations. These models are inspired by human biological nervous systems, even if there are various differences pertaining to the structural and functional properties of biological brains. The elementary constituents of deep learning models are neurons, which can be considered as functions that receive inputs and produce an output that is a weighted sum of the inputs fed through an activation function. Several models of neurons were proposed in the course of the years that are all based on learnable parameters called weights. In this paper we present a new type of artificial neuron, the double-weight neuron,characterized by additional learnable weights that lead to a more complex and accurate system. We tested a feed-forward and convolutional neural network consisting of double-weight neurons on the MNIST dataset, and we tested a convolution network on the CIFAR-10 dataset. For MNIST we find a $\approx 4\%$ and $\approx 1\%$ improved classification accuracy, respectively, when compared to a standard feed-forward and convolutional neural network built with the same sets of hyperparameters. For CIFAR-10 we find a $\approx 12\%$ improved classification accuracy. We thus conclude that this novel artificial neuron can be considered as a valuable alternative to common ones.

In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model compression and architecture search to learn models that are resource-efficient at inference time. Given a resource-intensive base architecture, DARC utilizes the training data to learn which sub-components can be replaced by cheaper alternatives. The high-level technique can be applied to any neural architecture, and we report experiments on state-of-the-art convolutional neural networks for image classification. For a WideResNet with $97.2\%$ accuracy on CIFAR-10, we improve single-sample inference speed by $2.28\times$ and memory footprint by $5.64\times$, with no accuracy loss. For a ResNet with $79.15\%$ Top1 accuracy on ImageNet, we improve batch inference speed by $1.29\times$ and memory footprint by $3.57\times$ with $1\%$ accuracy loss. We also give theoretical Rademacher complexity bounds in simplified cases, showing how DARC avoids overfitting despite over-parameterization.

For instance, earthquake wave is the observation Time series modeling aims to capture the intrinsic factors underpinning of crustal movements, while different actions like running and observed data and its evolution. However, most existing studies walking will cause differences in observations of a fitness-tracking ignore the evolutionary relations among these factors, which are device. Moreover, in practice, we often observe the combinatorial what cause the combinatorial evolution of a given time series. For evolution of data; that is, the observed time series being covered example, personal interests are intrinsic factors hidden behind users' by the influence of multiple factors, and especially the relations observable online shopping behaviors; consequently, a precise item among these factors. For example, an earthquake is the result of recommendation depends not only on discovering the item-interest quick transitions from smooth movements in the Earth's crust to relationship, but also on an understanding of how user interests intense ones, which cause a sudden release of energy in the Earth's shift over time. In this paper, we propose to represent complex and crust. Meanwhile, observing one's online shopping logs, precise dynamic relations among intrinsic factors of time series data by item recommendations rely on tracing and understanding the shift means of an evolutionary state graph structure.

The notion of twin systems is proposed to address the eXplainable AI (XAI) problem, where an uninterpretable black-box system is mapped to a white-box 'twin' that is more interpretable. In this short paper, we overview very recent work that advances a generic solution to the XAI problem, the so called twin system approach. The most popular twinning in the literature is that between an Artificial Neural Networks (ANN ) as a black box and Case Based Reasoning (CBR) system as a white-box, where the latter acts as an interpretable proxy for the former. We outline how recent work reviving this idea has applied it to deep learning methods. Furthermore, we detail the many fruitful directions in which this work may be taken; such as, determining the most (i) accurate feature-weighting methods to be used, (ii) appropriate deployments for explanatory cases, (iii) useful cases of explanatory value to users.

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited amount of labeled samples, which often leads to a considerable empirical distribution mismatch between labeled data and unlabeled data. To this end, we propose to align the empirical distributions of labeled and unlabeled data to alleviate the bias. On one hand, we adopt an adversarial training strategy to minimize the distribution distance between labeled and unlabeled data as inspired by domain adaptation works. On the other hand, to deal with the small sample size issue of labeled data, we also propose a simple interpolation strategy to generate pseudo training samples. Those two strategies can be easily implemented into existing deep neural networks. We demonstrate the effectiveness of our proposed approach on the benchmark SVHN and CIFAR10 datasets, on which we achieve new state-of-the-art error rates of $3.54\%$ and $10.09\%$, respectively. Our code will be available at \url{https://github.com/qinenergy/adanet}.

Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in remote sensing images, annotated data cannot be obtained in sufficient quantities. In this work, we propose a simple and efficient method for creating realistic targeted synthetic datasets in the remote sensing domain, leveraging the opportunities offered by game development engines. We provide a description of the pipeline for procedural geometry generation and rendering as well as an evaluation of the efficiency of produced datasets in a change detection scenario. Our evaluations demonstrate that our pipeline helps to improve the performance and convergence of deep learning models when the amount of real-world data is severely limited.

We present a large-scale empirical study of catastrophic forgetting (CF) in modern Deep Neural Network (DNN) models that perform sequential (or: incremental) learning. A new experimental protocol is proposed that enforces typical constraints encountered in application scenarios. As the investigation is empirical, we evaluate CF behavior on the hitherto largest number of visual classification datasets, from each of which we construct a representative number of Sequential Learning Tasks (SLTs) in close alignment to previous works on CF. Our results clearly indicate that there is no model that avoids CF for all investigated datasets and SLTs under application conditions. We conclude with a discussion of potential solutions and workarounds to CF, notably for the EWC and IMM models.

Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our network architecture allows us to obtain an attention mask for each feature while existing CNN visualization methods provide only a common attention mask for all features. We apply the proposed multi-channel attention mechanism to multi-attribute recognition task. We can obtain different attention mask for each feature and for each attribute. Those analyses give us deeper insight into the feature space of CNNs. Furthermore, our proposed attention mechanism naturally derives a method for improving the robustness of CNNs. From the observation of feature space based on the proposed attention mask, we demonstrate that we can obtain robust CNNs by intentionally emphasizing features that are important for attributes. The experimental results for the benchmark dataset show that the proposed method gives high human interpretability while accurately grasping the attributes of the data, and improves network robustness.

Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable training and poor sample efficiency. In our paper, we proposed an innovative optimization strategy by utilizing stochastic variance reduced gradient (SVRG) techniques. With extensive experiments on Atari domain, our method outperforms the deep q-learning baselines on 18 out of 20 games.

Bioacoustic sensors, sometimes known as autonomous recording units (ARUs), can record sounds of wildlife over long periods of time in scalable and minimally invasive ways. Deriving per-species abundance estimates from these sensors requires detection, classification, and quantification of animal vocalizations as individual acoustic events. Yet, variability in ambient noise, both over time and across sensors, hinders the reliability of current automated systems for sound event detection (SED), such as convolutional neural networks (CNN) in the time-frequency domain. In this article, we develop, benchmark, and combine several machine listening techniques to improve the generalizability of SED models across heterogeneous acoustic environments. As a case study, we consider the problem of detecting avian flight calls from a ten-hour recording of nocturnal bird migration, recorded by a network of six ARUs in the presence of heterogeneous background noise. Starting from a CNN yielding state-of-the-art accuracy on this task, we introduce two noise adaptation techniques, respectively integrating short-term (60-millisecond) and long-term (30-minute) context. First, we apply per-channel energy normalization (PCEN) in the time-frequency domain, which applies short-term automatic gain control to every subband in the mel-frequency spectrogram. Secondly, we replace the last dense layer in the network by a context-adaptive neural network (CA-NN) layer, i.e. an affine layer whose weights are dynamically adapted at prediction time by an auxiliary network taking long-term summary statistics of spectrotemporal features as input. We show that both techniques are helpful and complementary. [...] We release a pre-trained version of our best performing system under the name of BirdVoxDetect, a ready-to-use detector of avian flight calls in field recordings.