#### Generalization in Deep Learning

This paper explains why deep learning can generalize well, despite large capacity and possible algorithmic instability, nonrobustness, and sharp minima, effectively addressing an open problem in the literature. Based on our theoretical insight, this paper also proposes a family of new regularizatio…

#### A systematic study of the class imbalance problem in convolutional neural networks

CIFAR Convolutional Neural Network DNN IMAGENET MNIST

In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine l…

#### An Effective Training Method For Deep Convolutional Neural Network

CIFAR Convolutional Neural Network

In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs make the activation functions linear symmetric for their inp…

#### Projection Based Weight Normalization for Deep Neural Networks

CIFAR Convolutional Neural Network DNN gradient image IMAGENET MNIST

Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to constrain the incoming weights of each neuron to be unit-n…

#### Deep Convolutional Neural Networks as Generic Feature Extractors

CIFAR Convolutional Neural Network

Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task. However, the long time needed to train su…

#### Generative Adversarial Mapping Networks

CIFAR Generative Adversarial Network image MNIST

Generative Adversarial Networks (GANs) have shown impressive performance in generating photo-realistic images. They fit generative models by minimizing certain distance measure between the real image distribution and the generated data distribution. Several distance measures have been used, such as…

#### Confident Multiple Choice Learning

Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most applications involving deep neural networks, but they do not consid…

#### Neural Optimizer Search with Reinforcement Learning

CIFAR DNN gradient IMAGENET language Reinforcement Learning RNN

We present an approach to automate the process of discovering optimization methods, with a focus on deep learning architectures. We train a Recurrent Neural Network controller to generate a string in a domain specific language that describes a mathematical update equation based on a list of primiti…

#### Class-Splitting Generative Adversarial Networks

CIFAR clustering Generative Adversarial Network

Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still observed for the recently proposed Wasserstein GAN formulation which stabilized adversarial training and allows considerin…

#### Multi-Generator Generative Adversarial Nets

CIFAR game Generative Adversarial Network

We propose in this paper a novel approach to address the mode collapse problem in Generative Adversarial Nets (GANs) by training many generators. The training procedure is formulated as a minimax game among many generators, a classifier, and a discriminator. Generators produce data to fool the disc…

#### Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contri…

#### Adversarial Dropout for Supervised and Semi-supervised Learning

Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually biased inputs to enhance the generality, this paper introd…

#### Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification

CIFAR DNN image language MNIST security speech

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to adversarial manipulations at testing time. Specifically, suppo…

#### A Learning Approach to Secure Learning

Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied to ever increasing critical tasks like image recognition in…

#### Biased Importance Sampling for Deep Neural Network Training

CIFAR Convolutional Neural Network DNN gradient image language RNN

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning. In this paper, we show that the loss value can be used as an alternative im…

#### EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

CIFAR DNN image IMAGENET MNIST security

Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples – a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify. Existing methods for crafting adversarial examples are based on $L_2$ a…

#### Dual Discriminator Generative Adversarial Nets

CIFAR game Generative Adversarial Network IMAGENET MNIST

We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and re…

#### Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks

Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of self-driving cars as an example, small adversarial perturbat…

#### CuRTAIL: ChaRacterizing and Thwarting AdversarIal deep Learning

This paper proposes CuRTAIL, an end-to-end computing framework for characterizing and thwarting adversarial space in the context of Deep Learning (DL). The framework protects deep neural networks against adversarial samples, which are perturbed inputs carefully crafted by malicious entities to misl…

#### Overcoming Catastrophic Forgetting by Incremental Moment Matching

Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose incremental moment matching (IMM) to resolve this problem. IMM incrementally matches the moment of the posterior distribution of neural networks, whi…

#### The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis

Evolutionary deep intelligence was recently proposed as a method for achieving highly efficient deep neural network architectures over successive generations. Drawing inspiration from nature, we propose the incorporation of sexual evolutionary synthesis. Rather than the current asexual synthesis of…

#### Convolutional Gaussian Processes

We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional…

#### BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks

Deep neural networks are state of the art methods for many learning tasks due to their ability to extract increasingly better features at each network layer. However, the improved performance of additional layers in a deep network comes at the cost of added latency and energy usage in feedforward i…

#### Learning to Compose Domain-Specific Transformations for Data Augmentation

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual transformations, constructing and tuning the more sophisticated c…

#### Decision Stream: Cultivating Deep Decision Trees

Various modifications of decision trees have been extensively used during the past years due to their high efficiency and interpretability. Tree node splitting based on relevant feature selection is a key step of decision tree learning, at the same time being their major shortcoming: the recursive …