We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectified linear units (ReLUs), leaky ReLUs (LReLUs) and parametrized ReLUs (PRe-LUs), ELUs alleviate the vanishing gradient problem via the identity for positive values. However ELUs have improved learning characteristics compared to the units with other activation functions. In contrast to ReLUs, ELUs have negative values which allows them to push mean unit activations closer to zero like batch normalization but with lower computational complexity. Mean shifts toward zero speed up learning by bringing the normal gradient closer to the unit natural gradient because of a reduced bias shift effect. While LReLUs and PReLUs have negative values, too, they do not ensure a noise-robust deactivation state. ELUs saturate to a negative value with smaller inputs and thereby decrease the forward propagated variation and information. Therefore ELUs code the degree of presence of particular phenomena in the input, while they do not quantitatively model the degree of their absence. In experiments, ELUs lead not only to faster learning, but also to significantly better generalization performance than ReLUs and LReLUs on networks with more than 5 layers. On CIFAR-100 ELUs networks significantly outperform ReLU networks with batch normalization while batch normalization does not improve ELU networks. ELU networks are among the top 10 reported CIFAR-10 results and yield the best published result on CIFAR-100, without resorting to multi-view evaluation or model averaging. On ImageNet, ELU networks considerably speed up learning compared to a ReLU network with the same architecture, obtaining less than 10% classification error for a single crop, single model network.

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.

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batchnormalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning of the optimization problem and we speed up convergence of stochastic gradient descent. Our reparameterization is inspired by batch normalization but does not introduce any dependencies between the examples in a minibatch. This means that our method can also be applied successfully to recurrent models such as LSTMs and to noise-sensitive applications such as deep reinforcement learning or generative models, for which batch normalization is less well suited. Although our method is much simpler, it still provides much of the speed-up of full batch normalization. In addition, the computational overhead of our method is lower, permitting more optimization steps to be taken in the same amount of time. We demonstrate the usefulness of our method on applications in supervised image recognition, generative modelling, and deep reinforcement learning.

An activation function has a significant impact on the efficiency and robustness of the neural networks. As an alternative, we evolved a cutting-edge non-monotonic activation function, Negative Stimulated Hybrid Activation Function (Nish). It acts as a Rectified Linear Unit (ReLU) function for the positive region and a sinus-sigmoidal function for the negative region. In other words, it incorporates a sigmoid and a sine function and gaining new dynamics over classical ReLU. We analyzed the consistency of the Nish for different combinations of essential networks and most common activation functions using on several most popular benchmarks. From the experimental results, we reported that the accuracy rates achieved by the Nish is slightly better than compared to the Mish in classification.

目前，深层神经网络（DNN）主要使用一阶方法进行训练。其中一些方法（例如Adam，Adagrad和Rmsprop及其变体）通过使用对角线矩阵来预先处理随机梯度。最近，通过通过按层块 - diagonal矩阵对随机梯度进行预处理，已开发出有效的二阶方法，例如KFAC，K-BFGS，洗发水和TNT。在这里，我们提出了一种自适应的“迷你块Fisher（MBF）”预处理方法，其中在这两类方法之间。具体而言，我们的方法对经验渔民矩阵使用块对基近似值，在DNN中的每一层（无论是卷积还是馈送）和完全连接，相关的对角线本身都是块 - diagonal，并且由A组成。大量适度的迷你块。我们的新方法利用GPU的并行性来有效地对每一层的大量矩阵进行计算。因此，MBF的均值计算成本仅略高于一阶方法。将我们提出的方法的性能与在自动编码器和CNN问题上的几种基线方法进行了比较，以在时间效率和概括功率方面验证其有效性。最后，证明MBF的理想化版本线性收敛。

二阶优化器被认为具有加快神经网络训练的潜力，但是由于曲率矩阵的尺寸巨大，它们通常需要近似值才能计算。最成功的近似家庭是Kronecker因块状曲率估计值（KFAC）。在这里，我们结合了先前工作的工具，以评估确切的二阶更新和仔细消融以建立令人惊讶的结果：由于其近似值，KFAC与二阶更新无关，尤其是，它极大地胜过真实的第二阶段更新。订单更新。这一挑战广泛地相信，并立即提出了为什么KFAC表现如此出色的问题。为了回答这个问题，我们提出了强烈的证据，表明KFAC近似于一阶算法，该算法在神经元上执行梯度下降而不是权重。最后，我们表明，这种优化器通常会在计算成本和数据效率方面改善KFAC。

We introduce DropConnect, a generalization of Dropout (Hinton et al., 2012), for regularizing large fully-connected layers within neural networks. When training with Dropout, a randomly selected subset of activations are set to zero within each layer. DropConnect instead sets a randomly selected subset of weights within the network to zero. Each unit thus receives input from a random subset of units in the previous layer. We derive a bound on the generalization performance of both Dropout and DropConnect. We then evaluate DropConnect on a range of datasets, comparing to Dropout, and show state-of-the-art results on several image recognition benchmarks by aggregating multiple DropConnect-trained models.

我们研究了使用尖刺，现场依赖的随机矩阵理论研究迷你批次对深神经网络损失景观的影响。我们表明，批量黑森州的极值值的大小大于经验丰富的黑森州。我们还获得了类似的结果对Hessian的概括高斯牛顿矩阵近似。由于我们的定理，我们推导出作为批量大小的最大学习速率的分析表达式，为随机梯度下降（线性缩放）和自适应算法（例如ADAM（Square Root Scaling）提供了通知实际培训方案，例如光滑，非凸深神经网络。虽然随机梯度下降的线性缩放是在我们概括的更多限制性条件下导出的，但是适应优化者的平方根缩放规则是我们的知识，完全小说。随机二阶方法和自适应方法的百分比，我们得出了最小阻尼系数与学习率与批量尺寸的比率成比例。我们在Cifar-$ 100 $和ImageNet数据集上验证了我们的VGG / WimerEsnet架构上的索赔。根据我们对象检的调查，我们基于飞行学习率和动量学习者开发了一个随机兰齐齐竞争，这避免了对这些关键的超参数进行昂贵的多重评估的需求，并在预残留的情况下显示出良好的初步结果Cifar的architecure - $ 100 $。

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).

激活功能对于神经网络引入非线性至关重要。许多经验实验已经验证了各种激活功能，但有关激活功能的理论研究不足。在这项工作中，我们研究了激活功能对梯度方差的影响，并提出了一种使激活函数正常化的方法，以使所有层的梯度方差保持相同，以便神经网络可以实现更好的收敛性。首先，我们补充了先前的工作，以分析梯度方差的分析，在这种梯度的方差中，激活功能的影响仅在理想化的初始状态下，几乎不能保存在训练过程中，并获得了良好激活功能应尽可能满足的属性。其次，我们提供了一种将激活功能归一化并证明其对普遍激活功能的有效性的方法。通过观察实验，我们发现收敛速度与我们在前一部分中得出的属性大致相关。我们针对共同的激活函数进行了归一化激活函数的实验。结果表明，我们的方法始终优于其非标准化对应物。例如，就TOP-1的准确性而言，用CIFAR-100的RESNET50在RESNET50上归一化的Swish swilla swish swish swish。我们的方法通过简单地在完全连接的网络和残留网络中替换其归一化功能来改善性能。

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations. While batch normalization requires explicit normalization, neuron activations of SNNs automatically converge towards zero mean and unit variance. The activation function of SNNs are "scaled exponential linear units" (SELUs), which induce self-normalizing properties. Using the Banach fixed-point theorem, we prove that activations close to zero mean and unit variance that are propagated through many network layers will converge towards zero mean and unit variance -even under the presence of noise and perturbations. This convergence property of SNNs allows to (1) train deep networks with many layers, (2) employ strong regularization schemes, and (3) to make learning highly robust. Furthermore, for activations not close to unit variance, we prove an upper and lower bound on the variance, thus, vanishing and exploding gradients are impossible. We compared SNNs on (a) 121 tasks from the UCI machine learning repository, on (b) drug discovery benchmarks, and on (c) astronomy tasks with standard FNNs, and other machine learning methods such as random forests and support vector machines. For FNNs we considered (i) ReLU networks without normalization, (ii) batch normalization, (iii) layer normalization, (iv) weight normalization, (v) highway networks, and (vi) residual networks. SNNs significantly outperformed all competing FNN methods at 121 UCI tasks, outperformed all competing methods at the Tox21 dataset, and set a new record at an astronomy data set. The winning SNN architectures are often very deep.

虽然已知辍学是一种成功的正规化技术，但仍缺乏对导致成功的机制的见解。我们介绍了\ emph {重量膨胀}的概念，这增加了由权重协方差矩阵的列或行载体跨越的并行曲线的签名体积，并表明重量膨胀是增加PAC中概括的有效手段。 - bayesian设置。我们提供了一个理论上的论点，即辍学会导致体重扩大和对辍学和体重扩张之间相关性的广泛经验支持。为了支持我们的假设，即可以将重量扩张视为增强的概括能力的\ emph {指示器}，而不仅仅是副产品，我们还研究了实现重量扩展的其他方法（resp。\ contraction \ contraction ），发现它们通常会导致（分别\ \降低）的概括能力。这表明辍学是一种有吸引力的正规化器，因为它是一种用于获得体重扩展的计算廉价方法。这种洞察力证明了辍学者作为正规化器的作用，同时为确定正规化器铺平了道路，这些正规化器有望通过体重扩张来改善概括。

Helmholtz机器（HMS）是由两个Sigmoid信念网络（SBN）组成的一类生成模型，分别用作编码器和解码器。这些模型通常是使用称为唤醒 - 睡眠（WS）的两步优化算法对这些模型进行的，并且最近通过改进版本（例如重新恢复的尾流（RWS）和双向Helmholtz Machines（BIHM））进行了改进版本。 SBN中连接的局部性在与概率模型相关的Fisher信息矩阵中诱导稀疏性，并以细粒粒度的块状结构的形式引起。在本文中，我们利用自然梯度利用该特性来有效地训练SBN和HMS。我们提出了一种新颖的算法，称为“自然重新唤醒”（NRWS），该算法与其标准版本的几何适应相对应。以类似的方式，我们还引入了天然双向Helmholtz机器（NBIHM）。与以前的工作不同，我们将展示如何有效地计算自然梯度，而无需引入Fisher信息矩阵结构的任何近似值。在文献中进行的标准数据集进行的实验表明，NRW和NBIHM不仅在其非几何基准方面，而且在HMS的最先进培训算法方面都具有一致的改善。在训练后，汇聚速度以及对数可能达到的对数似然的值量化了改进。

深度学习使用由其重量进行参数化的神经网络。通常通过调谐重量来直接最小化给定损耗功能来训练神经网络。在本文中，我们建议将权重重新参数转化为网络中各个节点的触发强度的目标。给定一组目标，可以计算使得发射强度最佳地满足这些目标的权重。有人认为，通过我们称之为级联解压缩的过程，使用培训的目标解决爆炸梯度的问题，并使损失功能表面更加光滑，因此导致更容易，培训更快，以及潜在的概括，神经网络。它还允许更容易地学习更深层次和经常性的网络结构。目标对重量的必要转换有额外的计算费用，这是在许多情况下可管理的。在目标空间中学习可以与现有的神经网络优化器相结合，以额外收益。实验结果表明了使用目标空间的速度，以及改进的泛化的示例，用于全连接的网络和卷积网络，以及调用和处理长时间序列的能力，并使用经常性网络进行自然语言处理。

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema with low generalization error have a large proportion of almost-zero eigenvalues in the Hessian with very few positive or negative eigenvalues. We leverage upon this observation to construct a local-entropy-based objective function that favors well-generalizable solutions lying in large flat regions of the energy landscape, while avoiding poorly-generalizable solutions located in the sharp valleys. Conceptually, our algorithm resembles two nested loops of SGD where we use Langevin dynamics in the inner loop to compute the gradient of the local entropy before each update of the weights. We show that the new objective has a smoother energy landscape and show improved generalization over SGD using uniform stability, under certain assumptions. Our experiments on convolutional and recurrent networks demonstrate that Entropy-SGD compares favorably to state-of-the-art techniques in terms of generalization error and training time.

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate schemes, such as AdaGrad and Adam, and (2) accelerated schemes, such as heavy-ball and Nesterov momentum. In this paper, we propose a new optimization algorithm, Lookahead, that is orthogonal to these previous approaches and iteratively updates two sets of weights. Intuitively, the algorithm chooses a search direction by looking ahead at the sequence of "fast weights" generated by another optimizer. We show that Lookahead improves the learning stability and lowers the variance of its inner optimizer with negligible computation and memory cost. We empirically demonstrate Lookahead can significantly improve the performance of SGD and Adam, even with their default hyperparameter settings on ImageNet, CIFAR-10/100, neural machine translation, and Penn Treebank.

受生物神经元的启发，激活功能在许多现实世界中常用的任何人工神经网络的学习过程中起着重要作用。文献中已经提出了各种激活功能，用于分类和回归任务。在这项工作中，我们调查了过去已经使用的激活功能以及当前的最新功能。特别是，我们介绍了多年来激活功能的各种发展以及这些激活功能的优势以及缺点或局限性。我们还讨论了经典（固定）激活功能，包括整流器单元和自适应激活功能。除了基于表征的激活函数的分类法外，还提出了基于应用的激活函数的分类法。为此，对MNIST，CIFAR-10和CIFAR-100等分类数据集进行了各种固定和自适应激活函数的系统比较。近年来，已经出现了一个具有物理信息的机器学习框架，以解决与科学计算有关的问题。为此，我们还讨论了在物理知识的机器学习框架中使用的激活功能的各种要求。此外，使用Tensorflow，Pytorch和Jax等各种机器学习库之间进行了不同的固定和自适应激活函数进行各种比较。

为了对线性不可分离的数据进行分类，神经元通常被组织成具有至少一个隐藏层的多层神经网络。灵感来自最近神经科学的发现，我们提出了一种新的神经元模型以及一种新的激活函数，可以使用单个神经元来学习非线性决策边界。我们表明标准神经元随后是新颖的顶端枝晶激活（ADA）可以使用100 \％的精度来学习XOR逻辑函数。此外，我们在计算机视觉，信号处理和自然语言处理中进行五个基准数据集进行实验，即摩洛哥，utkface，crema-d，时尚mnist和微小的想象成，表明ADA和泄漏的ADA功能提供了卓越的结果用于各种神经网络架构的整流线性单元（Relu），泄漏的Relu，RBF和嗖嗖声，例如单隐层或两个隐藏层的多层的Perceptrons（MLPS）和卷积神经网络（CNNS），如LENET，VGG，RESET和字符级CNN。当我们使用具有顶端树突激活（Pynada）的金字塔神经元改变神经元的标准模型时，我们获得进一步的性能改进。我们的代码可用于：https://github.com/raduionescu/pynada。

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.