We have used information-theoretic ideas to derive a class of practical and nearly optimal schemes for adapting the size of a neural network. By removing unimportant weights from a network, several improvements can be expected: better generalization, fewer training examples required, and improved speed of learning and/or classification. The basic idea is to use second-derivative information to make a tradeoff between network complexity and training set error. Experiments confirm the usefulness of the methods on a real-world application.

We investigate the use of information from all second order derivatives of the error function to perfonn network pruning (i.e., removing unimportant weights from a trained network) in order to improve generalization, simplify networks, reduce hardware or storage requirements, increase the speed of further training, and in some cases enable rule extraction. Our method, Optimal Brain Surgeon (OBS), is Significantly better than magnitude-based methods and Optimal Brain Damage [Le Cun, Denker and Sol1a, 1990], which often remove the wrong weights. OBS permits the pruning of more weights than other methods (for the same error on the training set), and thus yields better generalization on test data. Crucial to OBS is a recursion relation for calculating the inverse Hessian matrix H-I from training data and structural information of the net. OBS permits a 90%, a 76%, and a 62% reduction in weights over backpropagation with weighL decay on three benchmark MONK's problems [Thrun et aI., 1991]. Of OBS, Optimal Brain Damage, and magnitude-based methods, only OBS deletes the correct weights from a trained XOR network in every case. Finally, whereas Sejnowski and Rosenberg [1987J used 18,000 weights in their NETtalk network, we used OBS to prune a network to just 1560 weights, yielding better generalization.

A quantitative and practical Bayesian framework is described for learning of mappings in feedforward networks. The framework makes possible (1) objective comparisons between solutions using alternative network architectures, (2) objective stopping rules for network pruning or growing procedures, (3) objective choice of magnitude and type of weight decay terms or additive regularizers (for penalizing large weights, etc.), (4) a measure of the effective number of well-determined parameters in a model, (5) quantified estimates of the error bars on network parameters and on network output, and (6) objective comparisons with alternative learning and interpolation models such as splines and radial basis functions. The Bayesian "evidence" automatically embodies "Occam's razor,'' penalizing overflexible and overcomplex models.The Bayesian approach helps detect poor underlying assumptions in learning models. For learning models well matched to a problem, a good correlation between generalization ability and the Bayesian evidence is obtained.This paper makes use of the Bayesian framework for regularization and model comparison described in the companion paper "Bayesian Interpolation" (MacKay 1992a). This framework is due to Gull and Skilling (Gull 1989). The Gaps in BackpropThere are many knobs on the black box of "backprop" [learning by backpropagation of errors (Rumelhart et al. 198611. Generally these knobs are set by rules of thumb, trial and error, and the use of reserved test data to assess generalization ability (or more sophisticated cross-validation). The knobs fall into two classes: (1) parameters that change the effective learning model, for example, number of hidden units, and weight decay

We present a new algorithm for nding low complexity neural networks with high generalization capability. The algorithm searches for a \ at" minimum of the error function. A at minimum is a large connected region in weight-space where the error remains approximately constant. An MDL-based, Bayesian argument suggests that at minima correspond to \simple" networks and low expected over tting. The argument is based on a Gibbs algorithm variant and a novel way of splitting generalization error into under tting and over tting error. Unlike many previous approaches, ours does not require Gaussian assumptions and does not depend on a \good" weight prior { instead we have a prior over input/output functions, thus taking into account net architecture and training set. Although our algorithm requires the computation of second order derivatives, it has backprop's order of complexity. Automatically, it e ectively prunes units, weights, and input lines. Various experiments with feedforward and recurrent nets are described. In an application to stock market prediction, at minimum search outperforms (1) conventional backprop, (2) weight decay, (3) \optimal brain surgeon" / \optimal brain damage". We also provide pseudo code of the algorithm (omitted from the NC-version).The appendix presents a detailed theoretical justi cation of our approach. Using a variant of the Gibbs algorithm, appendix A.1 de nes generalization, under tting and over tting error in a novel way. By de ning an appropriate prior over input-output functions, we postulate that the most probable network is a \ at" one. Appendix A.2 formally justi es the error function minimized by our algorithm. Appendix A.3 describes an e cient implementation of the algorithm. Appendix A.4 nally presents pseudo code of the algorithm. TASK / ARCHITECTURE / BOXESGeneralization task. The task is to approximate an unknown function f X Y mapping a nite set of possible inputs X R N to a nite set of possible outputs Y R K . A data set D is obtained from f (see appendix A.1). All training information is given by a nite set D 0 D. D 0 is called the training set. The pth element of D 0 is denoted by an input/target pair (x p ; y p ).Architecture/ Net functions. For simplicity, we will focus on a standard feedforward net (but in the experiments, we will use recurrent nets as well). The net has N input units, K output units, L weights, and di erentiable activation functions. It maps input vectors x 2 R N to output vectors o(w; x) 2 R K , where w is the L-dimensional weight vector, and the weight on the connection from unit j to i is denoted w ij . The net function induced by w is denoted net(w): for x 2 R N , net(w)(x) = o(w; x) = o 1 (w; x); o 2 (w; x); : : : ; o K 1 (w; x); o K (w; x) , where o i (w; x) denotes the i-th component of o(w; x), corresponding to output unit i. Training error. We use squared error E(net(w); D 0 ) := P (xp;yp)2D0 k y p o(w; x p ) k 2 , where k : k denotes the Euclidean norm.Tolerable error. To

We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-factored Approximate Curvature (K-FAC). K-FAC is based on an efficiently invertible approximation of a neural network's Fisher information matrix which is neither diagonal nor low-rank, and in some cases is completely non-sparse. It is derived by approximating various large blocks of the Fisher (corresponding to entire layers) as being the Kronecker product of two much smaller matrices. While only several times more expensive to compute than the plain stochastic gradient, the updates produced by K-FAC make much more progress optimizing the objective, which results in an algorithm that can be much faster than stochastic gradient descent with momentum in practice. And unlike some previously proposed approximate natural-gradient/Newton methods which use high-quality non-diagonal curvature matrices (such as Hessian-free optimization), K-FAC works very well in highly stochastic optimization regimes. This is because the cost of storing and inverting K-FAC's approximation to the curvature matrix does not depend on the amount of data used to estimate it, which is a feature typically associated only with diagonal or low-rank approximations to the curvature matrix.

Multilayer Neural Networks trained with the backpropagation algorithm constitute the best example of a successful Gradient-Based Learning technique. Given an appropriate network architecture, Gradient-Based Learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques.Real-life document recognition systems are composed of multiple modules including eld extraction, segmentation, recognition, and language modeling. A new learning paradigm, called Graph Transformer Networks (GTN), allows such multi-module systems to be trained globally using Gradient-Based methods so as to minimize an overall performance measure.Two systems for on-line handwriting recognition are described. Experiments demonstrate the advantage of global training, and the exibility of Graph Transformer Networks.A Graph Transformer Network for reading bank check is also described. It uses Convolutional Neural Network character recognizers combined with global training techniques to provides record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.

Pruning large neural networks while maintaining their performance is often desirable due to the reduced space and time complexity. In existing methods, pruning is done within an iterative optimization procedure with either heuristically designed pruning schedules or additional hyperparameters, undermining their utility. In this work, we present a new approach that prunes a given network once at initialization prior to training. To achieve this, we introduce a saliency criterion based on connection sensitivity that identifies structurally important connections in the network for the given task. This eliminates the need for both pretraining and the complex pruning schedule while making it robust to architecture variations. After pruning, the sparse network is trained in the standard way. Our method obtains extremely sparse networks with virtually the same accuracy as the reference network on the MNIST, CIFAR-10, and Tiny-ImageNet classification tasks and is broadly applicable to various architectures including convolutional, residual and recurrent networks. Unlike existing methods, our approach enables us to demonstrate that the retained connections are indeed relevant to the given task.

We present an application of back-propagation networks to handwritten digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task. The input of the network consists of normalized images of isolated digits. The method has 1 % error rate and about a 9% reject rate on zipcode digits provided

We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with finetuning by backpropagation-a computationally efficient procedure that maintains good generalization in the pruned network. We propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters. We focus on transfer learning, where large pretrained networks are adapted to specialized tasks. The proposed criterion demonstrates superior performance compared to other criteria, e.g. the norm of kernel weights or feature map activation, for pruning large CNNs after adaptation to fine-grained classification tasks (Birds-200 and Flowers-102) relaying only on the first order gradient information. We also show that pruning can lead to more than 10× theoretical reduction in adapted 3D-convolutional filters with a small drop in accuracy in a recurrent gesture classifier. Finally, we show results for the largescale ImageNet dataset to emphasize the flexibility of our approach.

在神经网络的经验风险景观中扁平最小值的性质已经讨论了一段时间。越来越多的证据表明他们对尖锐物质具有更好的泛化能力。首先，我们讨论高斯混合分类模型，并分析显示存在贝叶斯最佳点估算器，其对应于属于宽平区域的最小值。可以通过直接在分类器（通常是独立的）或学习中使用的可分解损耗函数上应用最大平坦度算法来找到这些估计器。接下来，我们通过广泛的数值验证将分析扩展到深度学习场景。使用两种算法，熵-SGD和复制-SGD，明确地包括在优化目标中，所谓的非局部平整度措施称为本地熵，我们一直提高常见架构的泛化误差（例如Resnet，CeffectnNet）。易于计算的平坦度测量显示与测试精度明确的相关性。

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs. In an application to computer vision, we show that our algorithms can reliably produce samples correctly classified by human subjects but misclassified in specific targets by a DNN with a 97% adversarial success rate while only modifying on average 4.02% of the input features per sample. We then evaluate the vulnerability of different sample classes to adversarial perturbations by defining a hardness measure. Finally, we describe preliminary work outlining defenses against adversarial samples by defining a predictive measure of distance between a benign input and a target classification.

这项调查的目的是介绍对深神经网络的近似特性的解释性回顾。具体而言，我们旨在了解深神经网络如何以及为什么要优于其他经典线性和非线性近似方法。这项调查包括三章。在第1章中，我们回顾了深层网络及其组成非线性结构的关键思想和概念。我们通过在解决回归和分类问题时将其作为优化问题来形式化神经网络问题。我们简要讨论用于解决优化问题的随机梯度下降算法以及用于解决优化问题的后传播公式，并解决了与神经网络性能相关的一些问题，包括选择激活功能，成本功能，过度适应问题和正则化。在第2章中，我们将重点转移到神经网络的近似理论上。我们首先介绍多项式近似中的密度概念，尤其是研究实现连续函数的Stone-WeierStrass定理。然后，在线性近似的框架内，我们回顾了馈电网络的密度和收敛速率的一些经典结果，然后在近似Sobolev函数中进行有关深网络复杂性的最新发展。在第3章中，利用非线性近似理论，我们进一步详细介绍了深度和近似网络与其他经典非线性近似方法相比的近似优势。

深度学习在广泛的AI应用方面取得了有希望的结果。较大的数据集和模型一致地产生更好的性能。但是，我们一般花费更长的培训时间，以更多的计算和沟通。在本调查中，我们的目标是在模型精度和模型效率方面提供关于大规模深度学习优化的清晰草图。我们调查最常用于优化的算法，详细阐述了大批量培训中出现的泛化差距的可辩论主题，并审查了解决通信开销并减少内存足迹的SOTA策略。

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.

这是一门专门针对STEM学生开发的介绍性机器学习课程。我们的目标是为有兴趣的读者提供基础知识，以在自己的项目中使用机器学习，并将自己熟悉术语作为进一步阅读相关文献的基础。在这些讲义中，我们讨论受监督，无监督和强化学习。注释从没有神经网络的机器学习方法的说明开始，例如原理分析，T-SNE，聚类以及线性回归和线性分类器。我们继续介绍基本和先进的神经网络结构，例如密集的进料和常规神经网络，经常性的神经网络，受限的玻尔兹曼机器，（变性）自动编码器，生成的对抗性网络。讨论了潜在空间表示的解释性问题，并使用梦和对抗性攻击的例子。最后一部分致力于加强学习，我们在其中介绍了价值功能和政策学习的基本概念。

Learning curves provide insight into the dependence of a learner's generalization performance on the training set size. This important tool can be used for model selection, to predict the effect of more training data, and to reduce the computational complexity of model training and hyperparameter tuning. This review recounts the origins of the term, provides a formal definition of the learning curve, and briefly covers basics such as its estimation. Our main contribution is a comprehensive overview of the literature regarding the shape of learning curves. We discuss empirical and theoretical evidence that supports well-behaved curves that often have the shape of a power law or an exponential. We consider the learning curves of Gaussian processes, the complex shapes they can display, and the factors influencing them. We draw specific attention to examples of learning curves that are ill-behaved, showing worse learning performance with more training data. To wrap up, we point out various open problems that warrant deeper empirical and theoretical investigation. All in all, our review underscores that learning curves are surprisingly diverse and no universal model can be identified.

We propose a simultaneous learning and pruning algorithm capable of identifying and eliminating irrelevant structures in a neural network during the early stages of training. Thus, the computational cost of subsequent training iterations, besides that of inference, is considerably reduced. Our method, based on variational inference principles using Gaussian scale mixture priors on neural network weights, learns the variational posterior distribution of Bernoulli random variables multiplying the units/filters similarly to adaptive dropout. Our algorithm, ensures that the Bernoulli parameters practically converge to either 0 or 1, establishing a deterministic final network. We analytically derive a novel hyper-prior distribution over the prior parameters that is crucial for their optimal selection and leads to consistent pruning levels and prediction accuracy regardless of weight initialization or the size of the starting network. We prove the convergence properties of our algorithm establishing theoretical and practical pruning conditions. We evaluate the proposed algorithm on the MNIST and CIFAR-10 data sets and the commonly used fully connected and convolutional LeNet and VGG16 architectures. The simulations show that our method achieves pruning levels on par with state-of the-art methods for structured pruning, while maintaining better test-accuracy and more importantly in a manner robust with respect to network initialization and initial size.

本文介绍了OptNet，该网络架构集成了优化问题（这里，专门以二次程序的形式），作为较大端到端可训练的深网络中的单个层。这些层在隐藏状态之间编码约束和复杂依赖性，传统的卷积和完全连接的层通常无法捕获。我们探索这种架构的基础：我们展示了如何使用敏感性分析，彼得优化和隐式差分的技术如何通过这些层和相对于层参数精确地区分;我们为这些层开发了一种高效的解算器，用于利用基于GPU的基于GPU的批处理在原始 - 双内部点法中解决，并且在求解的顶部几乎没有额外的成本提供了反向衰减梯度;我们突出了这些方法在几个问题中的应用。在一个值得注意的示例中，该方法学习仅在输入和输出游戏中播放Mini-sudoku（4x4），没有关于游戏规则的a-priori信息;这突出了OptNet比其他神经架构更好地学习硬限制的能力。

Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable sparse model to that of the largest trainable dense model. In this paper we introduce a method to train sparse neural networks with a fixed parameter count and a fixed computational cost throughout training, without sacrificing accuracy relative to existing dense-tosparse training methods. Our method updates the topology of the sparse network during training by using parameter magnitudes and infrequent gradient calculations. We show that this approach requires fewer floating-point operations (FLOPs) to achieve a given level of accuracy compared to prior techniques. We demonstrate state-of-the-art sparse training results on a variety of networks and datasets, including ResNet-50, MobileNets on Imagenet-2012, and RNNs on WikiText-103. Finally, we provide some insights into why allowing the topology to change during the optimization can overcome local minima encountered when the topology remains static * .

修剪神经网络可降低推理时间和记忆成本。在标准硬件上，如果修剪诸如特征地图之类的粗粒结构（例如特征地图），这些好处将特别突出。我们为二阶结构修剪（SOSP）设计了两种新型的基于显着性的方法，其中包括所有结构和层之间的相关性。我们的主要方法SOSP-H采用了创新的二阶近似，可以通过快速的Hessian-vector产品进行显着评估。 SOSP-H因此，尽管考虑到了完整的Hessian，但仍像一阶方法一样缩放。我们通过将SOSP-H与使用公认的Hessian近似值以及许多最先进方法进行比较来验证SOSP-H。尽管SOSP-H在准确性方面的表现或更好，但在可伸缩性和效率方面具有明显的优势。这使我们能够将SOSP-H扩展到大规模视觉任务，即使它捕获了网络所有层的相关性。为了强调我们修剪方法的全球性质，我们不仅通过删除预验证网络的结构，而且还通过检测建筑瓶颈来评估它们的性能。我们表明，我们的算法允许系统地揭示建筑瓶颈，然后将其删除以进一步提高网络的准确性。