Gao Huang

Densely Connected Convolutional Networks

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections—one between each layer and its subsequent layer—our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.

Trends in extreme learning machines

Extreme learning machine (ELM) has gained increasing interest from various research fields recently. In this review, we aim to report the current state of the theoretical research and practical advances on this subject. We first give an overview of ELM from the theoretical perspective, including the interpolation theory, universal approximation capability, and generalization ability. Then we focus on the various improvements made to ELM which further improve its stability, sparsity and accuracy under general or specific conditions. Apart from classification and regression, ELM has recently been extended for clustering, feature selection, representational learning and many other learning tasks. These newly emerging algorithms greatly expand the applications of ELM. From implementation aspect, hardware implementation and parallel computation techniques have substantially sped up the training of ELM, making it feasible for big data processing and real-time reasoning. Due to its remarkable efficiency, simplicity, and impressive generalization performance, ELM have been applied in a variety of domains, such as biomedical engineering, computer vision, system identification, and control and robotics. In this review, we try to provide a comprehensive view of these advances in ELM together with its future perspectives.

ReviewTrends in extreme learning machines: A review

Extreme learning machine (ELM) has gained increasing interest from various research fields recently. In this review, we aim to report the current state of the theoretical research and practical advances on this subject. We first give an overview of ELM from the theoretical perspective, including the interpolation theory, universal approximation capability, and generalization ability. Then we focus on the various improvements made to ELM which further improve its stability, sparsity and accuracy under general or specific conditions. Apart from classification and regression, ELM has recently been extended for clustering, feature selection, representational learning and many other learning tasks. These newly emerging algorithms greatly expand the applications of ELM. From implementation aspect, hardware implementation and parallel computation techniques have substantially sped up the training of ELM, making it feasible for big data processing and real-time reasoning. Due to its remarkable efficiency, simplicity, and impressive generalization performance, ELM have been applied in a variety of domains, such as biomedical engineering, computer vision, system identification, and control and robotics. In this review, we try to provide a comprehensive view of these advances in ELM together with its future perspectives.

Semi-Supervised and Unsupervised Extreme Learning Machines

Extreme learning machines (ELMs) have proven to be efficient and effective learning mechanisms for pattern classification and regression. However, ELMs are primarily applied to supervised learning problems. Only a few existing research papers have used ELMs to explore unlabeled data. In this paper, we extend ELMs for both semi-supervised and unsupervised tasks based on the manifold regularization, thus greatly expanding the applicability of ELMs. The key advantages of the proposed algorithms are as follows: 1) both the semi-supervised ELM (SS-ELM) and the unsupervised ELM (US-ELM) exhibit learning capability and computational efficiency of ELMs; 2) both algorithms naturally handle multiclass classification or multicluster clustering; and 3) both algorithms are inductive and can handle unseen data at test time directly. Moreover, it is shown in this paper that all the supervised, semi-supervised, and unsupervised ELMs can actually be put into a unified framework. This provides new perspectives for understanding the mechanism of random feature mapping, which is the key concept in ELM theory. Empirical study on a wide range of data sets demonstrates that the proposed algorithms are competitive with the state-of-the-art semi-supervised or unsupervised learning algorithms in terms of accuracy and efficiency.

Deep Networks with Stochastic Depth

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very deep networks but during training, for each mini-batch, randomly drop a subset of layers and bypass them with the identity function. This simple approach complements the recent success of residual networks. It reduces training time substantially and improves the test error significantly on almost all data sets that we used for evaluation. With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4.91 % on CIFAR-10).

Robust Support Vector Regression for Uncertain Input and Output Data

In this paper, a robust support vector regression (RSVR) method with uncertain input and output data is studied. First, the data uncertainties are investigated under a stochastic framework and two linear robust formulations are derived. Linear formulations robust to ellipsoidal uncertainties are also considered from a geometric perspective. Second, kernelized RSVR formulations are established for nonlinear regression problems. Both linear and nonlinear formulations are converted to second-order cone programming problems, which can be solved efficiently by the interior point method. Simulation demonstrates that the proposed method outperforms existing RSVRs in the presence of both input and output data uncertainties.

Gradient boosted feature selection

A feature selection algorithm should ideally satisfy four conditions: reliably extract relevant features; be able to identify non-linear feature interactions; scale linearly with the number of features and dimensions; allow the incorporation of known sparsity structure. In this work we propose a novel feature selection algorithm, Gradient Boosted Feature Selection (GBFS), which satisfies all four of these requirements. The algorithm is flexible, scalable, and surprisingly straight-forward to implement as it is based on a modification of Gradient Boosted Trees. We evaluate GBFS on several real world data sets and show that it matches or outperforms other state of the art feature selection algorithms. Yet it scales to larger data set sizes and naturally allows for domain-specific side information.

Orthogonal Least Squares Algorithm for Training Cascade Neural Networks

This paper proposes a novel constructive training algorithm for cascade neural networks. By reformulating the cascade neural network as a linear-in-the-parameters model, we use the orthogonal least squares (OLS) method to derive a novel objective function for training new hidden units. With this objective function, the sum of squared errors (SSE) of the network can be maximally reduced after each new hidden unit is added, thus leading to a network with less hidden units and better generalization performance. Furthermore, the proposed algorithm considers both the input weights training and output weights training in an integrated framework, which greatly simplifies the training of output weights. The effectiveness of the proposed algorithm is demonstrated by simulation results.

Discriminative clustering via extreme learning machine

Discriminative clustering is an unsupervised learning framework which introduces the discriminative learning rule of supervised classification into clustering. The underlying assumption is that a good partition (clustering) of the data should yield high discrimination, namely, the partitioned data can be easily classified by some classification algorithms. In this paper, we propose three discriminative clustering approaches based on Extreme Learning Machine (ELM). The first algorithm iteratively trains weighted ELM (W-ELM) classifier to gradually maximize the data discrimination. The second and third methods are both built on Fishers Linear Discriminant Analysis (LDA); but one approach adopts alternative optimization, while the other leverages kernel k-means. We show that the proposed algorithms can be easily implemented, and yield competitive clustering accuracy on real world data sets compared to state-of-the-art clustering methods.

Unsupervised neighborhood component analysis for clustering

In this paper, we propose a novel unsupervised distance metric learning algorithm. The proposed algorithm aims to maximize a stochastic variant of the leave-one-out K-nearest neighbor (KNN) score on unlabeled data, which performs distance metric learning and clustering simultaneously. We show that the joint distance metric learning and clustering problem is formulated as a trace optimization problem, and can be solved efficiently by an iterative algorithm. Moreover, the proposed approach can also learn a low dimensional projection of high dimensional data, thus it can serve as an unsupervised dimensionality reduction tool, which is capable of performing joint dimensionality reduction and clustering. We validate our method on a number of benchmark datasets, and the results demonstrate the effectiveness of the proposed algorithm.