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.

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.

这项正在进行的工作旨在为统计学习提供统一的介绍，从诸如GMM和HMM等经典模型到现代神经网络（如VAE和扩散模型）缓慢地构建。如今，有许多互联网资源可以孤立地解释这一点或新的机器学习算法，但是它们并没有（也不能在如此简短的空间中）将这些算法彼此连接起来，或者与统计模型的经典文献相连现代算法出现了。同样明显缺乏的是一个单一的符号系统，尽管对那些已经熟悉材料的人（如这些帖子的作者）不满意，但对新手的入境造成了重大障碍。同样，我的目的是将各种模型（尽可能）吸收到一个用于推理和学习的框架上，表明（以及为什么）如何以最小的变化将一个模型更改为另一个模型（其中一些是新颖的，另一些是文献中的）。某些背景当然是必要的。我以为读者熟悉基本的多变量计算，概率和统计以及线性代数。这本书的目标当然不是​​完整性，而是从基本知识到过去十年中极强大的新模型的直线路径或多或少。然后，目标是补充而不是替换，诸如Bishop的\ emph {模式识别和机器学习}之类的综合文本，该文本现在已经15岁了。

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。

现代深度学习方法构成了令人难以置信的强大工具，以解决无数的挑战问题。然而，由于深度学习方法作为黑匣子运作，因此与其预测相关的不确定性往往是挑战量化。贝叶斯统计数据提供了一种形式主义来理解和量化与深度神经网络预测相关的不确定性。本教程概述了相关文献和完整的工具集，用于设计，实施，列车，使用和评估贝叶斯神经网络，即使用贝叶斯方法培训的随机人工神经网络。

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.

Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

Recent years have witnessed a growth in mathematics for deep learning--which seeks a deeper understanding of the concepts of deep learning with mathematics, and explores how to make it more robust--and deep learning for mathematics, where deep learning algorithms are used to solve problems in mathematics. The latter has popularised the field of scientific machine learning where deep learning is applied to problems in scientific computing. Specifically, more and more neural network architectures have been developed to solve specific classes of partial differential equations (PDEs). Such methods exploit properties that are inherent to PDEs and thus solve the PDEs better than classical feed-forward neural networks, recurrent neural networks, and convolutional neural networks. This has had a great impact in the area of mathematical modeling where parametric PDEs are widely used to model most natural and physical processes arising in science and engineering, In this work, we review such methods and extend them for parametric studies as well as for solving the related inverse problems. We equally proceed to show their relevance in some industrial applications.

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.

预测性编码提供了对皮质功能的潜在统一说明 - 假设大脑的核心功能是最小化有关世界生成模型的预测错误。该理论与贝叶斯大脑框架密切相关，在过去的二十年中，在理论和认知神经科学领域都产生了重大影响。基于经验测试的预测编码的改进和扩展的理论和数学模型，以及评估其在大脑中实施的潜在生物学合理性以及该理论所做的具体神经生理学和心理学预测。尽管存在这种持久的知名度，但仍未对预测编码理论，尤其是该领域的最新发展进行全面回顾。在这里，我们提供了核心数学结构和预测编码的逻辑的全面综述，从而补充了文献中最新的教程。我们还回顾了该框架中的各种经典和最新工作，从可以实施预测性编码的神经生物学现实的微电路到预测性编码和广泛使用的错误算法的重新传播之间的紧密关系，以及对近距离的调查。预测性编码和现代机器学习技术之间的关系。

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization, highlighting the importance of scale normalization, and making a connection between sharpness and PAC-Bayes theory. We then investigate how well the measures explain different observed phenomena.

In this thesis, we consider two simple but typical control problems and apply deep reinforcement learning to them, i.e., to cool and control a particle which is subject to continuous position measurement in a one-dimensional quadratic potential or in a quartic potential. We compare the performance of reinforcement learning control and conventional control strategies on the two problems, and show that the reinforcement learning achieves a performance comparable to the optimal control for the quadratic case, and outperforms conventional control strategies for the quartic case for which the optimal control strategy is unknown. To our knowledge, this is the first time deep reinforcement learning is applied to quantum control problems in continuous real space. Our research demonstrates that deep reinforcement learning can be used to control a stochastic quantum system in real space effectively as a measurement-feedback closed-loop controller, and our research also shows the ability of AI to discover new control strategies and properties of the quantum systems that are not well understood, and we can gain insights into these problems by learning from the AI, which opens up a new regime for scientific research.

贝叶斯网络是一种图形模型，用于编码感兴趣的变量之间的概率关系。当与统计技术结合使用时，图形模型对数据分析具有几个优点。一个，因为模型对所有变量中的依赖性进行编码，因此它易于处理缺少某些数据条目的情况。二，贝叶斯网络可以用于学习因果关系，因此可以用来获得关于问题域的理解并预测干预的后果。三，因为该模型具有因果和概率语义，因此是结合先前知识（通常出现因果形式）和数据的理想表示。四，贝叶斯网络与贝叶斯网络的统计方法提供了一种有效和原则的方法，可以避免数据过剩。在本文中，我们讨论了从先前知识构建贝叶斯网络的方法，总结了使用数据来改善这些模型的贝叶斯统计方法。关于后一项任务，我们描述了学习贝叶斯网络的参数和结构的方法，包括使用不完整数据学习的技术。此外，我们还联系了贝叶斯网络方法，以学习监督和无监督学习的技术。我们说明了使用真实案例研究的图形建模方法。

在过去几十年中，已经提出了各种方法，用于估计回归设置中的预测间隔，包括贝叶斯方法，集合方法，直接间隔估计方法和保形预测方法。重要问题是这些方法的校准：生成的预测间隔应该具有预定义的覆盖水平，而不会过于保守。在这项工作中，我们从概念和实验的角度审查上述四类方法。结果来自各个域的基准数据集突出显示从一个数据集中的性能的大波动。这些观察可能归因于违反某些类别的某些方法所固有的某些假设。我们说明了如何将共形预测用作提供不具有校准步骤的方法的方法的一般校准程序。

In many engineering optimization problems, the number of function evaluations is severely limited by time or cost. These problems pose a special challenge to the field of global optimization, since existing methods often require more function evaluations than can be comfortably afforded. One way to address this challenge is to fit response surfaces to data collected by evaluating the objective and constraint functions at a few points. These surfaces can then be used for visualization, tradeoff analysis, and optimization. In this paper, we introduce the reader to a response surface methodology that is especially good at modeling the nonlinear, multimodal functions that often occur in engineering. We then show how these approximating functions can be used to construct an efficient global optimization algorithm with a credible stopping rule. The key to using response surfaces for global optimization lies in balancing the need to exploit the approximating surface (by sampling where it is minimized) with the need to improve the approximation (by sampling where prediction error may be high). Striking this balance requires solving certain auxiliary problems which have previously been considered intractable, but we show how these computational obstacles can be overcome.

用于估计模型不确定性的线性拉普拉斯方法在贝叶斯深度学习社区中引起了人们的重新关注。该方法提供了可靠的误差线，并接受模型证据的封闭式表达式，从而可以选择模型超参数。在这项工作中，我们检查了这种方法背后的假设，尤其是与模型选择结合在一起。我们表明，这些与一些深度学习的标准工具（构成近似方法和归一化层）相互作用，并为如何更好地适应这种经典方法对现代环境提出建议。我们为我们的建议提供理论支持，并在MLP，经典CNN，具有正常化层，生成性自动编码器和变压器的剩余网络上进行经验验证它们。