本文调查了从紧凑型代表和存储训练参数的角度来看深神经网络（DNN）压缩。我们探讨了用于DNN参数的跨层架构 - 不可知表示共享的先前被忽视的机会。为此，我们从DNN架构中解耦了前馈参数并利用添加量量化，用于图像描述符的极端损耗压缩方法，以紧凑地表示参数。然后，在任务目标上是Fineetune的，以提高任务准确性。我们对MobileNet-V2，VGG-11，Reset-50进行了广泛的实验，具有用于分类，检测和分割任务的修剪培训的Pruned DNN。概念上简单的方案始终如一地优于迭代非结构化修剪。在ILSVRC12分类挑战上以76.1％的高精度应用于Reset-50，它实现了7.2美元的价格，没有准确性损失和15.3美元的准确度。进一步的分析表明，在网络层中可能经常发生表示共享，并且整个DNN的学习共享表示可以以与多个单独的部分压缩模型相同的压缩比以相同的压缩比实现更好的精度。我们释放Pytorch码以促进资源受限设备上的DNN部署，并对DNN参数的有效表示和存储的未来研究。

深度神经网络（DNN）的记录断裂性能具有沉重的参数化，导致外部动态随机存取存储器（DRAM）进行存储。 DRAM访问的禁用能量使得在资源受限的设备上部署DNN是不普遍的，呼叫最小化重量和数据移动以提高能量效率。我们呈现SmartDeal（SD），算法框架，以进行更高成本的存储器存储/访问的较低成本计算，以便在推理和培训中积极提高存储和能量效率。 SD的核心是一种具有结构约束的新型重量分解，精心制作以释放硬件效率潜力。具体地，我们将每个重量张量分解为小基矩阵的乘积以及大的结构稀疏系数矩阵，其非零被量化为-2的功率。由此产生的稀疏和量化的DNN致力于为数据移动和重量存储而大大降低的能量，因为由于稀疏的比特 - 操作和成本良好的计算，恢复原始权重的最小开销。除了推理之外，我们采取了另一次飞跃来拥抱节能培训，引入创新技术，以解决培训时出现的独特障碍，同时保留SD结构。我们还设计专用硬件加速器，充分利用SD结构来提高实际能源效率和延迟。我们在不同的设置中对多个任务，模型和数据集进行实验。结果表明：1）应用于推理，SD可实现高达2.44倍的能效，通过实际硬件实现评估; 2）应用于培训，储存能量降低10.56倍，减少了10.56倍和4.48倍，与最先进的训练基线相比，可忽略的准确性损失。我们的源代码在线提供。

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briefly discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark datasets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and predictive performance.

Model quantization enables the deployment of deep neural networks under resource-constrained devices. Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings, i.e., codewords, while the index needs to be restored to 32-bit during computation. Binary and other low-precision quantization methods can reduce the model size up to 32$\times$, however, at the cost of a considerable accuracy drop. In this paper, we propose an efficient framework for ternary quantization to produce smaller and more accurate compressed models. By integrating hyperspherical learning, pruning and reinitialization, our proposed Hyperspherical Quantization (HQ) method reduces the cosine distance between the full-precision and ternary weights, thus reducing the bias of the straight-through gradient estimator during ternary quantization. Compared with existing work at similar compression levels ($\sim$30$\times$, $\sim$40$\times$), our method significantly improves the test accuracy and reduces the model size.

Inference time, model size, and accuracy are three key factors in deep model compression. Most of the existing work addresses these three key factors separately as it is difficult to optimize them all at the same time. For example, low-bit quantization aims at obtaining a faster model; weight sharing quantization aims at improving compression ratio and accuracy; and mixed-precision quantization aims at balancing accuracy and inference time. To simultaneously optimize bit-width, model size, and accuracy, we propose pruning ternary quantization (PTQ): a simple, effective, symmetric ternary quantization method. We integrate L2 normalization, pruning, and the weight decay term to reduce the weight discrepancy in the gradient estimator during quantization, thus producing highly compressed ternary weights. Our method brings the highest test accuracy and the highest compression ratio. For example, it produces a 939kb (49$\times$) 2bit ternary ResNet-18 model with only 4\% accuracy drop on the ImageNet dataset. It compresses 170MB Mask R-CNN to 5MB (34$\times$) with only 2.8\% average precision drop. Our method is verified on image classification, object detection/segmentation tasks with different network structures such as ResNet-18, ResNet-50, and MobileNetV2.

深度学习技术在各种任务中都表现出了出色的有效性，并且深度学习具有推进多种应用程序（包括在边缘计算中）的潜力，其中将深层模型部署在边缘设备上，以实现即时的数据处理和响应。一个关键的挑战是，虽然深层模型的应用通常会产生大量的内存和计算成本，但Edge设备通常只提供非常有限的存储和计算功能，这些功能可能会在各个设备之间差异很大。这些特征使得难以构建深度学习解决方案，以释放边缘设备的潜力，同时遵守其约束。应对这一挑战的一种有希望的方法是自动化有效的深度学习模型的设计，这些模型轻巧，仅需少量存储，并且仅产生低计算开销。该调查提供了针对边缘计算的深度学习模型设计自动化技术的全面覆盖。它提供了关键指标的概述和比较，这些指标通常用于量化模型在有效性，轻度和计算成本方面的水平。然后，该调查涵盖了深层设计自动化技术的三类最新技术：自动化神经体系结构搜索，自动化模型压缩以及联合自动化设计和压缩。最后，调查涵盖了未来研究的开放问题和方向。

模型压缩旨在将深神经网络（DNN）部署在具有有限的计算和存储资源的移动设备上。但是，大多数现有模型压缩方法依赖于手动定义的规则，这些规则需要域专业知识。 DNN基本上是计算图形，其包含丰富的结构信息。在本文中，我们的目标是从DNNS结构信息找到合适的压缩策略。我们提出了一种自动图形编码器 - 解码器模型压缩（AGMC）方法与图形神经网络（GNN）和加强学习（RL）结合。我们将目标DNN模拟为图形并使用GNN自动学习DNN的嵌入物。我们将我们的方法与基于规则的DNN嵌入模型压缩方法进行了比较，以显示我们方法的有效性。结果表明，基于学习的DNN嵌入实现了更好的性能和更高的搜索步骤的压缩比。我们在过度参数化和移动友好的DNN上进行了评估方法，并将我们的方法与基于手工和学习的模型压缩方法进行了比较。在参数化DNN（如Resnet-56）上，我们的方法分别优于3.36 \％$ 4.36 \％$ 4.36 \％$ 4.36 \％$ 2.56 \％$ 2.56 \％的准确性。此外，在MobileNet-V2上，我们达到了比最先进的方法更高的压缩比，只需0.93±％$精度损失。

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. To address this limitation, we introduce "deep compression", a three stage pipeline: pruning, trained quantization and Huffman coding, that work together to reduce the storage requirement of neural networks by 35× to 49× without affecting their accuracy. Our method first prunes the network by learning only the important connections. Next, we quantize the weights to enforce weight sharing, finally, we apply Huffman coding. After the first two steps we retrain the network to fine tune the remaining connections and the quantized centroids. Pruning, reduces the number of connections by 9× to 13×; Quantization then reduces the number of bits that represent each connection from 32 to 5. On the ImageNet dataset, our method reduced the storage required by AlexNet by 35×, from 240MB to 6.9MB, without loss of accuracy. Our method reduced the size of VGG-16 by 49× from 552MB to 11.3MB, again with no loss of accuracy. This allows fitting the model into on-chip SRAM cache rather than off-chip DRAM memory. Our compression method also facilitates the use of complex neural networks in mobile applications where application size and download bandwidth are constrained. Benchmarked on CPU, GPU and mobile GPU, compressed network has 3× to 4× layerwise speedup and 3× to 7× better energy efficiency.

诸如智能手机和自治车辆的移动设备越来越依赖深神经网络（DNN）来执行复杂的推理任务，例如图像分类和语音识别等。但是，在移动设备上连续执行整个DNN可以快速消耗其电池。虽然任务卸载到云/边缘服务器可能会降低移动设备的计算负担，但信道质量，网络和边缘服务器负载中的不稳定模式可能导致任务执行的显着延迟。最近，已经提出了基于分割计算（SC）的方法，其中DNN被分成在移动设备上和边缘服务器上执行的头部和尾模型。最终，这可能会降低带宽使用以及能量消耗。另一种叫做早期退出（EE）的方法，列车模型在架构中呈现多个“退出”，每个都提供越来越高的目标准确性。因此，可以根据当前条件或应用需求进行准确性和延迟之间的权衡。在本文中，我们通过呈现最相关方法的比较，对SC和EE策略进行全面的综合调查。我们通过提供一系列引人注目的研究挑战来结束论文。

重量修剪是一种有效的模型压缩技术，可以解决在移动设备上实现实时深神经网络（DNN）推断的挑战。然而，由于精度劣化，难以利用硬件加速度，以及某些类型的DNN层的限制，难以降低的应用方案具有有限的应用方案。在本文中，我们提出了一般的细粒度的结构化修剪方案和相应的编译器优化，适用于任何类型的DNN层，同时实现高精度和硬件推理性能。随着使用我们的编译器优化所支持的不同层的灵活性，我们进一步探讨了确定最佳修剪方案的新问题，了解各种修剪方案的不同加速度和精度性能。两个修剪方案映射方法，一个是基于搜索，另一个是基于规则的，建议自动推导出任何给定DNN的每层的最佳修剪规则和块大小。实验结果表明，我们的修剪方案映射方法，以及一般细粒化结构修剪方案，优于最先进的DNN优化框架，最高可达2.48 $ \ times $和1.73 $ \ times $ DNN推理加速在CiFar-10和Imagenet DataSet上没有准确性损失。

我们日常生活中的深度学习是普遍存在的，包括自驾车，虚拟助理，社交网络服务，医疗服务，面部识别等，但是深度神经网络在训练和推理期间需要大量计算资源。该机器学习界主要集中在模型级优化（如深度学习模型的架构压缩），而系统社区则专注于实施级别优化。在其间，在算术界中提出了各种算术级优化技术。本文在模型，算术和实施级技术方面提供了关于资源有效的深度学习技术的调查，并确定了三种不同级别技术的资源有效的深度学习技术的研究差距。我们的调查基于我们的资源效率度量定义，阐明了较低级别技术的影响，并探讨了资源有效的深度学习研究的未来趋势。

Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Accordingly, techniques that enable efficient processing of DNNs to improve energy efficiency and throughput without sacrificing application accuracy or increasing hardware cost are critical to the wide deployment of DNNs in AI systems.This article aims to provide a comprehensive tutorial and survey about the recent advances towards the goal of enabling efficient processing of DNNs. Specifically, it will provide an overview of DNNs, discuss various hardware platforms and architectures that support DNNs, and highlight key trends in reducing the computation cost of DNNs either solely via hardware design changes or via joint hardware design and DNN algorithm changes. It will also summarize various development resources that enable researchers and practitioners to quickly get started in this field, and highlight important benchmarking metrics and design considerations that should be used for evaluating the rapidly growing number of DNN hardware designs, optionally including algorithmic co-designs, being proposed in academia and industry.The reader will take away the following concepts from this article: understand the key design considerations for DNNs; be able to evaluate different DNN hardware implementations with benchmarks and comparison metrics; understand the trade-offs between various hardware architectures and platforms; be able to evaluate the utility of various DNN design techniques for efficient processing; and understand recent implementation trends and opportunities.

二进制神经网络（BNNS）已经证明了它们能够以可比精度（DNNS）的准确性来解决复杂任务的能力，同时还降低了计算能力和存储要求并提高处理速度。这些属性使它们成为开发和部署基于DNN的应用程序（IOT）设备的吸引人的替代方法。尽管最近有所改善，但它们的压缩因素可能会导致一些资源非常有限的设备可能导致不足。在这项工作中，我们提出了稀疏的二进制神经网络（SBNNS），这是一种新颖的模型和训练方案，它引入了BNN中的稀疏性和一种新的量化函数，以使网络的权重进行二进制。提出的SBNN能够达到高压因子，并减少了推理时的操作和参数数量。我们还提供工具来协助SBNN设计，同时尊重硬件资源约束。我们通过三个数据集的线性和卷积网络上的一组实验来研究我们方法对不同压缩因子的概括属性。我们的实验证实，SBNNS可以达到高压缩率，而不会损害概括，同时进一步降低了BNNS的操作，使SBNNS成为以廉价，低成本，限量资源的IOT设备和传感器部署DNN的可行选择。

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning, according to a certain criterion, redundant weights are pruned and important weights are kept to best preserve the accuracy. In this work, we make several surprising observations which contradict common beliefs. For all state-of-the-art structured pruning algorithms we examined, fine-tuning a pruned model only gives comparable or worse performance than training that model with randomly initialized weights. For pruning algorithms which assume a predefined target network architecture, one can get rid of the full pipeline and directly train the target network from scratch. Our observations are consistent for multiple network architectures, datasets, and tasks, which imply that: 1) training a large, over-parameterized model is often not necessary to obtain an efficient final model, 2) learned "important" weights of the large model are typically not useful for the small pruned model, 3) the pruned architecture itself, rather than a set of inherited "important" weights, is more crucial to the efficiency in the final model, which suggests that in some cases pruning can be useful as an architecture search paradigm. Our results suggest the need for more careful baseline evaluations in future research on structured pruning methods. We also compare with the "Lottery Ticket Hypothesis" (Frankle & Carbin, 2019), and find that with optimal learning rate, the "winning ticket" initialization as used in Frankle & Carbin (2019) does not bring improvement over random initialization. * Equal contribution. † Work done while visiting UC Berkeley.

混合精确的深神经网络达到了硬件部署所需的能源效率和吞吐量，尤其是在资源有限的情况下，而无需牺牲准确性。但是，不容易找到保留精度的最佳每层钻头精度，尤其是在创建巨大搜索空间的大量模型，数据集和量化技术中。为了解决这一困难，最近出现了一系列文献，并且已经提出了一些实现有希望的准确性结果的框架。在本文中，我们首先总结了文献中通常使用的量化技术。然后，我们对混合精液框架进行了彻底的调查，该调查是根据其优化技术进行分类的，例如增强学习和量化技术，例如确定性舍入。此外，讨论了每个框架的优势和缺点，我们在其中呈现并列。我们最终为未来的混合精液框架提供了指南。

在本文中，我们介绍了一种新颖的神经网络重量压缩方法。在我们的方法中，我们将重量张量存储为稀疏，量化的矩阵因子，其产品在推理过程中即时计算以生成目标模型的权重。我们使用预计的梯度下降方法来找到重量张量的量化和稀疏分解。我们表明，这种方法可以看作是重量SVD，矢量量化和稀疏PCA的统一。结合端到端微调，我们的方法超出了或与以前的最先进方法相提并论，就精度和模型大小之间的权衡而言。我们的方法适用于中等压缩方案，与矢量量化和极端压缩方案不同。

嵌入式和个人物联网设备由微控制器单元（MCU）供电，其极端资源稀缺是依赖于设备的深度学习推断的应用的主要障碍。与通常需要执行神经网络的内容相比，存储器，内存和计算能力较少的秩序，对网络架构上的严格结构约束并呼叫专业模型压缩方法。在这项工作中，我们为卷积神经网络提出了可分散的结构化网络修剪方法，它集成了模型的MCU特定的资源使用和参数重要性反馈，以获得高度压缩但准确的分类模型。我们的方法（a）提高了高达80倍的模型的关键资源使用; （b）在培训型号的同时迭代地修剪，导致没有开销甚至改善培训时间; （c）与现有MCU的特定方法相比，在比较多的时间内生产具有匹配或改进的资源使用的压缩模型。压缩模型可供下载。

深度神经网络（DNN）已成为移动和嵌入式系统中的普遍存在的技术，用于图像/对象识别和分类。执行多个DNN的趋势同时加剧了资源受限移动设备上满足严格延迟/准确性要求的现有限制。现有技术通过根据资源动态缩放模型大小来探索精度资源权衡的光。然而，这种模型缩放方法接近迫在眉睫的挑战：（i）模型尺寸的大空间探索，（ii）对不同模型组合的培训时间非常长。在本文中，我们介绍了Legodnn，一种用于在移动视觉系统中运行多DNN工作负载的轻质块粒度缩放解决方案。 Legodnn仅通过在DNN中提取和培训少数常见块（例如，在VGG和RENET中的VGG和8中的8中）来保证短模型培训时间。在运行时，Legodnn最佳地结合了这些块的后代模型，以最大限度地在特定资源和延迟约束下最大限度地提高精度，同时通过DNN的智能块级缩放来降低切换开销。我们在Tensorflow Lite中实现Legodnn，并通过一组普遍的DNN模型，广泛地评估了最先进的技术（浮标缩放，知识蒸馏和模型压缩）。评估结果表明，乐高达在模型尺寸下提供了1,296倍至279,936倍，而在不增加训练时间的情况下，推断准确性的提高高达31.74％，降低缩放能耗减少了71.07％。

彩票票证假设（LTH）表明，密集的模型包含高度稀疏的子网（即获奖门票），可以隔离培训以完全准确。尽管做出了许多激动人心的努力，但仍有一个“常识”很少受到挑战：通过迭代级修剪（IMP）发现了一张获胜的票，因此由此产生的修剪子网仅具有非结构化的稀疏性。这一差距限制了在实践中赢得门票的吸引力，因为高度不规则的稀疏模式在硬件上加速的挑战是挑战性的。同时，直接将结构化修剪替换为非结构化的修剪，以更严重地损害绩效，并且通常无法找到获胜的票。在本文中，我们证明了第一个积极的结果是，总体上可以有效地找到结构上稀疏的获胜票。核心思想是在每一轮（非结构化）IMP之后附加“后处理技术”，以实施结构稀疏的形成。具体而言，我们首先在某些被认为很重要的通道中“重新填充”修剪元素，然后“重新组”非零元素以创建灵活的群体结构模式。我们确定的渠道和团体结构子网都赢得了彩票，并以现有硬件很容易支持的大量推理加速。广泛的实验，在多个网络骨架的不同数据集上进行，一致验证了我们的建议，表明LTH的硬件加速障碍现在已被删除。具体而言，结构上的获胜票最多可获得{64.93％，64.84％，60.23％}的运行时间节省，以{36％〜80％，74％，58％}的稀疏性在{Cifar，cifar，tiny-imageNet，imageNet}上保持可比较的精度。代码在https://github.com/vita-group/structure-lth上。

The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the model size; 2) decrease the run-time memory footprint; and 3) lower the number of computing operations, without compromising accuracy. This is achieved by enforcing channel-level sparsity in the network in a simple but effective way. Different from many existing approaches, the proposed method directly applies to modern CNN architectures, introduces minimum overhead to the training process, and requires no special software/hardware accelerators for the resulting models. We call our approach network slimming, which takes wide and large networks as input models, but during training insignificant channels are automatically identified and pruned afterwards, yielding thin and compact models with comparable accuracy. We empirically demonstrate the effectiveness of our approach with several state-of-the-art CNN models, including VGGNet, ResNet and DenseNet, on various image classification datasets. For VGGNet, a multi-pass version of network slimming gives a 20× reduction in model size and a 5× reduction in computing operations.