事实证明，诸如层归一化（LN）和批处理（BN）之类的方法可有效改善复发性神经网络（RNN）的训练。但是，现有方法仅在一个特定的时间步骤中仅使用瞬时信息进行归一化，而归一化的结果是具有时间无关分布的预反应状态。该实现无法解释RNN的输入和体系结构中固有的某些时间差异。由于这些网络跨时间步骤共享权重，因此也可能需要考虑标准化方案中时间步长之间的连接。在本文中，我们提出了一种称为“分类时间归一化”（ATN）的归一化方法，该方法保留了来自多个连续时间步骤的信息，并使用它们归一化。这种设置使我们能够将更长的时间依赖项引入传统的归一化方法，而无需引入任何新的可训练参数。我们介绍了梯度传播的理论推导，并证明了权重缩放不变属性。我们将ATN应用于LN的实验表明，对各种任务（例如添加，复制和DENOISE问题和语言建模问题）表现出一致的改进。

近年来，使用正交矩阵已被证明是通过训练，稳定性和收敛尤其是控制梯度来改善复发性神经网络（RNN）的一种有希望的方法。通过使用各种门和记忆单元，封闭的复发单元（GRU）和长期短期记忆（LSTM）体系结构解决了消失的梯度问题，但它们仍然容易出现爆炸梯度问题。在这项工作中，我们分析了GRU中的梯度，并提出了正交矩阵的使用，以防止梯度问题爆炸并增强长期记忆。我们研究了在哪里使用正交矩阵，并提出了基于Neumann系列的缩放尺度的Cayley转换，以训练GRU中的正交矩阵，我们称之为Neumann-cayley Orthoconal orthoconal Gru或简单的NC-GRU。我们介绍了有关几个合成和现实世界任务的模型的详细实验，这些实验表明NC-GRU明显优于GRU以及其他几个RNN。

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。

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.

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach through stacked convolutions, which can be more efficient since they allow parallelization over sequential tokens. We propose a novel simplified gating mechanism that outperforms Oord et al. (2016b) and investigate the impact of key architectural decisions. The proposed approach achieves state-of-the-art on the WikiText-103 benchmark, even though it features longterm dependencies, as well as competitive results on the Google Billion Words benchmark. Our model reduces the latency to score a sentence by an order of magnitude compared to a recurrent baseline. To our knowledge, this is the first time a non-recurrent approach is competitive with strong recurrent models on these large scale language tasks.

Learning hierarchical structures in sequential data -- from simple algorithmic patterns to natural language -- in a reliable, generalizable way remains a challenging problem for neural language models. Past work has shown that recurrent neural networks (RNNs) struggle to generalize on held-out algorithmic or syntactic patterns without supervision or some inductive bias. To remedy this, many papers have explored augmenting RNNs with various differentiable stacks, by analogy with finite automata and pushdown automata (PDAs). In this paper, we improve the performance of our recently proposed Nondeterministic Stack RNN (NS-RNN), which uses a differentiable data structure that simulates a nondeterministic PDA, with two important changes. First, the model now assigns unnormalized positive weights instead of probabilities to stack actions, and we provide an analysis of why this improves training. Second, the model can directly observe the state of the underlying PDA. Our model achieves lower cross-entropy than all previous stack RNNs on five context-free language modeling tasks (within 0.05 nats of the information-theoretic lower bound), including a task on which the NS-RNN previously failed to outperform a deterministic stack RNN baseline. Finally, we propose a restricted version of the NS-RNN that incrementally processes infinitely long sequences, and we present language modeling results on the Penn Treebank.

我们介绍了块状变压器，该变压器以序列的反复方式应用变压器层，并且相对于序列长度具有线性复杂性。我们的复发单元在训练过程中在代币的块而不是单个令牌上运行，并利用块内并行计算，以便有效利用加速器硬件。单元本身非常简单。它仅仅是一个变压器层：它使用自我注意事项和交叉注意力来有效计算大量状态向量和令牌上的复发函数。我们的设计部分受到LSTM单元的启发，它使用LSTM风格的大门，但它可以将典型的LSTM单元缩放为几个数量级。我们的复发实现在计算时间和参数计数中都具有相同的成本作为传统的变压器层，但是在很长的序列中，语言建模任务中的语言建模任务的困惑极大地改善了。我们的模型比远程变压器XL基线的表现宽大，同时运行的速度是两倍。我们证明了它在PG19（书籍），Arxiv论文和GitHub源代码上的有效性。我们的代码已发布为开​​源。

We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach that directly finds these equilibrium points via root-finding. Such a method is equivalent to running an infinite depth (weight-tied) feedforward network, but has the notable advantage that we can analytically backpropagate through the equilibrium point using implicit differentiation. Using this approach, training and prediction in these networks require only constant memory, regardless of the effective "depth" of the network. We demonstrate how DEQs can be applied to two state-of-the-art deep sequence models: self-attention transformers and trellis networks. On large-scale language modeling tasks, such as the WikiText-103 benchmark, we show that DEQs 1) often improve performance over these stateof-the-art models (for similar parameter counts); 2) have similar computational requirements to existing models; and 3) vastly reduce memory consumption (often the bottleneck for training large sequence models), demonstrating an up-to 88% memory reduction in our experiments. The code is available at https://github. com/locuslab/deq.

这项研究介绍了一个称为批处理层归一化（BLN）的新的归一化层，以减少深神经网络层中内部协变量转移的问题。作为批处理和层归一化的组合版本，BLN自适应地将适当的重量放在迷你批处理上，并基于迷你批次的逆尺寸，在学习过程中将输入标准化为层。它还使用微型批量统计或人口统计数据，在推理时间执行精确的计算，并在推理时间进行较小的更改。使用迷你批量或人口统计的决策过程使BLN具有在模型的超参数优化过程中发挥全面作用的能力。 BLN的关键优势是对独立于输入数据的理论分析的支持，其统计配置在很大程度上取决于执行的任务，培训数据的量和批次的大小。测试结果表明，BLN的应用潜力及其更快的收敛性在卷积和复发性神经网络中都比批处理归一化和层归一化。实验的代码在线公开可用（https://github.com/a2amir/batch-layer-normalization）。

有效地对远程依赖性建模是序列建模的重要目标。最近，使用结构化状态空间序列（S4）层的模型在许多远程任务上实现了最先进的性能。 S4层将线性状态空间模型（SSM）与深度学习技术结合在一起，并利用HIPPO框架进行在线功能近似以实现高性能。但是，该框架导致了架构约束和计算困难，使S4方法变得复杂，可以理解和实施。我们重新审视这样的想法，即遵循河马框架对于高性能是必要的。具体而言，我们替换了许多独立的单输入单输出（SISO）SSM的库S4层与一个多输入的多输出（MIMO）SSM一起使用，并具有降低的潜在尺寸。 MIMO系统的缩小潜在维度允许使用有效的并行扫描，从而简化了将S5层应用于序列到序列转换所需的计算。此外，我们将S5 SSM的状态矩阵初始化，其近似与S4 SSMS使用的河马级矩阵近似，并表明这是MIMO设置的有效初始化。 S5与S4在远程任务上的表现相匹配，包括在远程竞技场基准的套件中平均达到82.46％，而S4的80.48％和最佳的变压器变体的61.41％。

We introduce a method to train Quantized Neural Networks (QNNs) -neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At traintime the quantized weights and activations are used for computing the parameter gradients. During the forward pass, QNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations. As a result, power consumption is expected to be drastically reduced. We trained QNNs over the MNIST, CIFAR-10, SVHN and ImageNet datasets. The resulting QNNs achieve prediction accuracy comparable to their 32-bit counterparts. For example, our quantized version of AlexNet with 1-bit weights and 2-bit activations achieves 51% top-1 accuracy. Moreover, we quantize the parameter gradients to 6-bits as well which enables gradients computation using only bit-wise operation. Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits. Last but not least, we programmed a binary matrix multiplication GPU kernel with which it is possible to run our MNIST QNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The QNN code is available online.

自回旋运动平均值（ARMA）模型是经典的，可以说是模型时间序列数据的最多研究的方法之一。它具有引人入胜的理论特性，并在从业者中广泛使用。最近的深度学习方法普及了经常性神经网络（RNN），尤其是长期记忆（LSTM）细胞，这些细胞已成为神经时间序列建模中最佳性能和最常见的构件之一。虽然对具有长期效果的时间序列数据或序列有利，但复杂的RNN细胞并不总是必须的，有时甚至可能不如更简单的复发方法。在这项工作中，我们介绍了ARMA细胞，这是一种在神经网络中的时间序列建模的更简单，模块化和有效的方法。该单元可以用于存在复发结构的任何神经网络体系结构中，并自然地使用矢量自动进程处理多元时间序列。我们还引入了Convarma细胞作为空间相关时间序列的自然继任者。我们的实验表明，所提出的方法在性能方面与流行替代方案具有竞争力，同时由于其简单性而变得更加强大和引人注目。

Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backpropagation. However, we also show that for classical RNNs, LSTM and GRU networks the distance of data points between recurrent calls that can be reproduced this way is highly limited (compared to even a loose connection between data points) and subject to various constraints imposed by the type and size of the RNN in question. This implies the existence of a hard limit (way below the information-theoretic one) for the distance between related data points within which RNNs are still able to recognize said relation.

差异私有随机梯度下降（DPSGD）是基于差分隐私（DP）范例的随机梯度下降的变化，这可以减轻来自在训练数据中存在敏感信息的隐私威胁。然而，具有DPSGD的培训深度神经网络的一个主要缺点是模型精度的降低。本文研究了标准化层对DPSGD性能的影响。我们证明标准化层显着影响了深度神经网络与嘈杂参数的效用，应该被视为DPSGD培训的基本成分。特别是，我们提出了一种新的方法，用于将批量标准化与DPSGD集成，而不会产生额外的隐私损失。通过我们的方法，我们能够培训更深的网络并实现更好的效用隐私权衡。

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. 1 Compared to recurrent models, computations over all elements can be fully parallelized during training to better exploit the GPU hardware and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.

长期数据的分类是一个重要的机器学习任务，并出现在许多应用程序中。经常性的神经网络，变压器和卷积神经网络是从顺序数据学习的三种主要技术。在这些方法中，在时间序列回归中缩放到非常长序列的时间卷积网络（TCN）已经取得了显着的进展。但是，对于序列分类的TCNS的性能并不令人满意，因为它们在最后位置使用偏斜连接协议和输出类。这种不对称限制了它们对分类的性能，这取决于整个序列。在这项工作中，我们提出了一种称为循环扩张卷积神经网络（CDIL-CNN）的对称的多尺度架构，其中每个位置具有相同的机会从前一层处接收来自其他位置的信息。我们的模型在所有位置提供分类登录，我们可以应用一个简单的集合学习来实现更好的决定。我们在各种长期数据集上测试了CDIL-CNN。实验结果表明，我们的方法在许多最先进的方法上具有卓越的性能。

We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network [23] but unlike the model in that work, it is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings. It can also be seen as an extension of RNNsearch [2] to the case where multiple computational steps (hops) are performed per output symbol. The flexibility of the model allows us to apply it to tasks as diverse as (synthetic) question answering [22] and to language modeling. For the former our approach is competitive with Memory Networks, but with less supervision. For the latter, on the Penn TreeBank and Text8 datasets our approach demonstrates comparable performance to RNNs and LSTMs. In both cases we show that the key concept of multiple computational hops yields improved results.

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, they are often treated as black-box models and as such it is difficult to understand what exactly they learn as well as how they arrive at a particular prediction. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications. This mechanism, which we term state-regularization, makes RNNs transition between a finite set of learnable states. We evaluate state-regularized RNNs on (1) regular languages for the purpose of automata extraction; (2) non-regular languages such as balanced parentheses and palindromes where external memory is required; and (3) real-word sequence learning tasks for sentiment analysis, visual object recognition and text categorisation. We show that state-regularization (a) simplifies the extraction of finite state automata that display an RNN's state transition dynamic; (b) forces RNNs to operate more like automata with external memory and less like finite state machines, which potentiality leads to a more structural memory; (c) leads to better interpretability and explainability of RNNs by leveraging the probabilistic finite state transition mechanism over time steps.

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference -sometimes prohibitively so in the case of very large data sets and large models. Several authors have also charged that NMT systems lack robustness, particularly when input sentences contain rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using residual connections as well as attention connections from the decoder network to the encoder. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. To directly optimize the translation BLEU scores, we consider refining the models by using reinforcement learning, but we found that the improvement in the BLEU scores did not reflect in the human evaluation. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system.