We introduce the chi-square test neural network: a single hidden layer backpropagation neural network using chi-square test theorem to redefine the cost function and the error function. The weights and thresholds are modified using standard backpropagation algorithm. The proposed approach has the advantage of making consistent data distribution over training and testing sets. It can be used for binary classification. The experimental results on real world data sets indicate that the proposed algorithm can significantly improve the classification accuracy comparing to related approaches.
Learning Local Feature Aggregation Functions with Backpropagation
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
本文介绍了一个家庭的局部特征聚合函数和一种新的方法来估计它们的参数，使它们产生最佳表示分类（或任何任务，可以表示为成本函数最小化问题）。为了实现这一点，我们将局部特征聚合函数与分类器成本函数组合在一起，并反向传播该成本函数的梯度，以更新局部特征聚合函数参数。合成数据集上的实验表明，我们的方法发现的参数，除了局部特征空间模型的类相关信息。在图像和视频数据集上对各种运动和视觉描述符进行的进一步实验表明，我们的方法比其他最先进的局部特征聚合函数（如Bag of Words，Fisher Vectors和VLAD）表现更好。
NTT Communication Science Laboratories（NTT通信科学研究所）；NTT Software Innovation Center（NTT软件创新中心）
Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural network-based meta-learning method for supervised anomaly detection. The proposed method improves the anomaly detection performance on unseen tasks, which contains a few labeled normal and anomalous instances, by meta-training with various datasets. With a meta-learning framework, quick adaptation to each task and its effective backpropagation are important since the model is trained by the adaptation for each epoch. Our…
PCANet and its variants provided good accuracy results for classification tasks. However, despite the importance of network depth in achieving good classification accuracy, these networks were trained with a maximum of nine layers. In this paper, we introduce a residual compensation convolutional network, which is the first PCANet-like network trained with hundreds of layers while improving classification accuracy. The design of the proposed network consists of several convolutional layers, each followed by post-processing steps and a classifier. To correct the classification errors and signif…
UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）；Facebook AI Research（脸书人工智能研究院）
Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outperforming Euclidean neural networks (ENNs) on datasets with known semantic hierarchies. However, HNNs underperform ENNs on standard benchmarks without clear hierarchies, greatly restricting HNNs' applicability in practice. Our key insight is that HNNs' poorer general classification performance results from vanishing gradients during backpropagation, caused by their hybrid archi…
Local learning for stable backpropagation-free neural network training towards physical learning
Department of Materials Science and Engineering, Delft University of Technology（材料科学与工程系，代尔夫特理工大学）；Department of Precision and Microsystems Engineering, Delft University of Technology（精密与微系统工程系，代尔夫特理工大学）；Department of Intelligent Systems, Delft University of Technology（智能系统系，代尔夫特理工大学）
MRC Brain Network Dynamics Unit, University of Oxford（牛津大学医学研究委员会脑网络动力学研究中心）；University of Oxford（牛津大学）
The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning. However, it requires sequential backward updates and non-local computations, which make it challenging to parallelize at scale and is unlike how learning works in the brain. Neuroscience-inspired learning algorithms, however, such as \emph{predictive coding}, which utilize local learning, have the potential to overcome these limitations and advance beyond current deep learning technologies. While predictive coding originated in theoretical neuroscience as a model of…
Multiclass Graph-Based Large Margin Classifiers: Unified Approach for Support Vectors and Neural Networks
Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais（电气工程联合培养项目，巴西米纳斯吉拉斯联邦大学）；Department of Computer and Systems, Universidade Federal de Ouro Preto（计算机与系统系，巴西欧鲁普穆联邦大学）
In this work we explore recurrent representations of leaky integrate and fire neurons operating at a timescale equal to their absolute refractory period. Our coarse time scale approximation is obtained using a probability distribution function for spike arrivals that is homogeneously distributed over this time interval. This leads to a discrete representation that exhibits the same dynamics as the continuous model, enabling efficient large scale simulations and backpropagation through the recurrent implementation. We use this approach to explore the training of deep spiking neural networks inc…
We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise. The hypothesis is that a generative model, that combines the state transitions of a hidden Markov model (HMM) and the neural network based probability distributions for the hidden states of the HMM, can provide a robust classification performance. The combined model is called normalizing-flow mixture model based HMM (NMM-HMM). It can be trained using a combination of expectation-maximization (EM) and backpropagation. We verify the improved robustness of NMM-HMM class…
Bone Marrow Transplant, a gradational rescue for a wide range of disorders emanating from the bone marrow, is an efficacious surgical treatment. Several risk factors, such as post-transplant illnesses, new malignancies, and even organ damage, can impair long-term survival. Therefore, technologies like Machine Learning are deployed for investigating the survival prediction of BMT receivers along with the influences that limit their resilience. In this study, an efficient survival classification model is presented in a comprehensive manner, incorporating the Chi-squared feature selection method …
There has been a recent surge in the field of Explainable AI (XAI) which tackles the problem of providing insights into the behavior of black-box machine learning models. Within this field, \textit{feature attribution} encompasses methods which assign relevance scores to input features and visualize them as a heatmap. Designing flexible accelerators for multiple such algorithms is challenging since the hardware mapping of these algorithms has not been studied yet. In this work, we first analyze the dataflow of gradient backpropagation based feature attribution algorithms to determine the resou…
We investigate optimal posteriors for recently introduced \cite{begin2016pac} chi-squared divergence based PAC-Bayesian bounds in terms of nature of their distribution, scalability of computations, and test set performance. For a finite classifier set, we deduce bounds for three distance functions: KL-divergence, linear and squared distances. Optimal posterior weights are proportional to deviations of empirical risks, usually with subset support. For uniform prior, it is sufficient to search among posteriors on classifier subsets ordered by these risks. We show the bound minimization for linea…
Meitu（美图）；The Hang Seng University of Hong Kong（香港恒生大学）
汉语分词是汉语语言理解的一项基本任务。近年来，基于神经网络的模型在解决领域内的CWS任务方面取得了优异的性能。去年，一种新的语言表示模型BERT（Bidirectional Encoder Representation from Transformers）被提出作为许多自然语言任务的骨干模型，并重新定义了相应的性能。BERT的优良性能激励我们将其应用于CWS任务的解决。通过对第二届国际汉语分词大赛的基准数据集进行深入的实验，我们得到了一些敏锐的观察。BERT可以稍微提高性能，即使数据集包含标签不一致的问题。当应用充分学习的特征时，Softmax，一个更简单的分类器，可以达到与更复杂的分类器相同的性能，例如，条件随机场（CRF）。BERT的性能通常随着模型大小的增加而增加。BERT提取的特征也可以作为其他神经网络模型的良好候选。
The University of Tokyo（东京大学）；National Institute of Technology, Tokuyama College（德山工业高等专门学校）；University of Tsukuba（筑波大学）
We propose a conditional generative adversarial network (GAN) incorporating humans' perceptual evaluations. A deep neural network (DNN)-based generator of a GAN can represent a real-data distribution accurately but can never represent a human-acceptable distribution, which are ranges of data in which humans accept the naturalness regardless of whether the data are real or not. A HumanGAN was proposed to model the human-acceptable distribution. A DNN-based generator is trained using a human-based discriminator, i.e., humans' perceptual evaluations, instead of the GAN's DNN-based discriminator. …
Institute of Statistics and Data Science, Nanjing Audit University（南京审计大学统计与数据科学学院）
China has made great achievements in electric power industry during the long-term deepening of reform and opening up. However, the complex regional economic, social and natural conditions, electricity resources are not evenly distributed, which accounts for the electricity deficiency in some regions of China. It is desirable to develop a robust electricity forecasting model. Motivated by which, we propose a Panel Semiparametric Quantile Regression Neural Network (PSQRNN) by utilizing the artificial neural network and semiparametric quantile regression. The PSQRNN can explore a potential linear…
Columbia University（哥伦比亚大学）；Recognition Technologies, Inc.（识别技术公司）
Two new approaches to accent classification and conversion are presented and explored, respectively. The first topic is Chinese accent classification/recognition. The second topic is the use of encoder-decoder models for end-to-end Chinese accent conversion, where the classifier in the first topic is used for the training of the accent converter encoder-decoder model. Experiments using different features and model are performed for accent recognition. These features include MFCCs and spectrograms. The classifier models were TDNN and 1D-CNN. On the MAGICDATA dataset with 5 classes of accents, t…
Fast, simple and accurate handwritten digit classification by training shallow neural network classifiers with the 'extreme learning machine' algorithm
University of South Australia（南澳大学）；The University of Western Sydney（西悉尼大学）
Training neural networks with discrete stochastic variables presents a unique challenge. Backpropagation is not directly applicable, nor are the reparameterization tricks used in networks with continuous stochastic variables. To address this challenge, we present Hindsight Network Credit Assignment (HNCA), a novel gradient estimation algorithm for networks of discrete stochastic units. HNCA works by assigning credit to each unit based on the degree to which its output influences its immediate children in the network. We prove that HNCA produces unbiased gradient estimates with reduced variance…
