亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Despite their simple intuition, convolutions are more tedious to analyze than dense layers, which complicates the generalization of theoretical and algorithmic ideas. We provide a new perspective onto convolutions through tensor networks (TNs) which allow reasoning about the underlying tensor multiplications by drawing diagrams, and manipulating them to perform function transformations, sub-tensor access, and fusion. We demonstrate this expressive power by deriving the diagrams of various autodiff operations and popular approximations of second-order information with full hyper-parameter support, batching, channel groups, and generalization to arbitrary convolution dimensions. Further, we provide convolution-specific transformations based on the connectivity pattern which allow to re-wire and simplify diagrams before evaluation. Finally, we probe computational performance, relying on established machinery for efficient TN contraction. Our TN implementation speeds up a recently-proposed KFAC variant up to 4.5x and enables new hardware-efficient tensor dropout for approximate backpropagation.

Voltage Overscaling (VOS) is one of the well-known techniques to increase the energy efficiency of arithmetic units. Also, it can provide significant lifetime improvements, while still meeting the accuracy requirements of inherently error-resilient applications. This paper proposes a generic accuracy-configurable multiplier that employs the VOS at a coarse-grained level (block-level) to reduce the control logic required for applying VOS and its associated overheads, thus enabling a high degree of trade-off between energy consumption and output quality. The proposed configurable Block-Level VOS-based (BL-VOS) multiplier relies on employing VOS in a multiplier composed of smaller blocks, where applying VOS in different blocks results in structures with various output accuracy levels. To evaluate the proposed concept, we implement 8-bit and 16-bit BL-VOS multipliers with various blocks width in a 15-nm FinFET technology. The results show that the proposed multiplier achieves up to 15% lower energy consumption and up to 21% higher output accuracy compared to the state-of-the-art VOS-based multipliers. Also, the effects of Process Variation (PV) and Bias Temperature Instability (BTI) induced delay on the proposed multiplier are investigated. Finally, the effectiveness of the proposed multiplier is studied for two different image processing applications, in terms of quality and energy efficiency.

Deep neural networks (DNNs) have demonstrated remarkable performance across various tasks, including image and speech recognition. However, maximizing the effectiveness of DNNs requires meticulous optimization of numerous hyperparameters and network parameters through training. Moreover, high-performance DNNs entail many parameters, which consume significant energy during training. In order to overcome these challenges, researchers have turned to spiking neural networks (SNNs), which offer enhanced energy efficiency and biologically plausible data processing capabilities, rendering them highly suitable for sensory data tasks, particularly in neuromorphic data. Despite their advantages, SNNs, like DNNs, are susceptible to various threats, including adversarial examples and backdoor attacks. Yet, the field of SNNs still needs to be explored in terms of understanding and countering these attacks. This paper delves into backdoor attacks in SNNs using neuromorphic datasets and diverse triggers. Specifically, we explore backdoor triggers within neuromorphic data that can manipulate their position and color, providing a broader scope of possibilities than conventional triggers in domains like images. We present various attack strategies, achieving an attack success rate of up to 100\% while maintaining a negligible impact on clean accuracy. Furthermore, we assess these attacks' stealthiness, revealing that our most potent attacks possess significant stealth capabilities. Lastly, we adapt several state-of-the-art defenses from the image domain, evaluating their efficacy on neuromorphic data and uncovering instances where they fall short, leading to compromised performance.

Recently, many studies have shed light on the high adaptivity of deep neural network methods in nonparametric regression models, and their superior performance has been established for various function classes. Motivated by this development, we study a deep neural network method to estimate the drift coefficient of a multi-dimensional diffusion process from discrete observations. We derive generalization error bounds for least squares estimates based on deep neural networks and show that they achieve the minimax rate of convergence up to a logarithmic factor when the drift function has a compositional structure.

The line coverage problem is to find efficient routes for coverage of linear features by one or more resource-constrained robots. Linear features model environments such as road networks, power lines, and oil and gas pipelines. We define two modes of travel for robots: servicing and deadheading. A robot services a feature if it performs task-specific actions, e.g., taking images, as it traverses the feature; otherwise, it is deadheading. Traversing the environment incurs costs (e.g., travel time) and demands on resources (e.g., battery life). Servicing and deadheading can have different cost and demand functions, and we further permit them to be direction dependent. We model the environment as a graph and provide an integer linear program. As the problem is NP-hard, we develop a fast and efficient heuristic algorithm, Merge-Embed-Merge (MEM). By exploiting the constructive property of the MEM algorithm, we develop algorithms for line coverage of large graphs with multiple depots. Furthermore, we efficiently incorporate turning costs and nonholonomic constraints into the algorithm. We benchmark the algorithms on road networks and demonstrate them in experiments using aerial robots.

We hypothesize that due to the greedy nature of learning in multi-modal deep neural networks, these models tend to rely on just one modality while under-fitting the other modalities. Such behavior is counter-intuitive and hurts the models' generalization, as we observe empirically. To estimate the model's dependence on each modality, we compute the gain on the accuracy when the model has access to it in addition to another modality. We refer to this gain as the conditional utilization rate. In the experiments, we consistently observe an imbalance in conditional utilization rates between modalities, across multiple tasks and architectures. Since conditional utilization rate cannot be computed efficiently during training, we introduce a proxy for it based on the pace at which the model learns from each modality, which we refer to as the conditional learning speed. We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning. The proposed algorithm improves the model's generalization on three datasets: Colored MNIST, Princeton ModelNet40, and NVIDIA Dynamic Hand Gesture.

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. However, with the progressive improvements in deep learning models, their number of parameters, latency, resources required to train, etc. have all have increased significantly. Consequently, it has become important to pay attention to these footprint metrics of a model as well, not just its quality. We present and motivate the problem of efficiency in deep learning, followed by a thorough survey of the five core areas of model efficiency (spanning modeling techniques, infrastructure, and hardware) and the seminal work there. We also present an experiment-based guide along with code, for practitioners to optimize their model training and deployment. We believe this is the first comprehensive survey in the efficient deep learning space that covers the landscape of model efficiency from modeling techniques to hardware support. Our hope is that this survey would provide the reader with the mental model and the necessary understanding of the field to apply generic efficiency techniques to immediately get significant improvements, and also equip them with ideas for further research and experimentation to achieve additional gains.

The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their biological counterparts, sparse networks generalize just as well, if not better than, the original dense networks. Sparsity can reduce the memory footprint of regular networks to fit mobile devices, as well as shorten training time for ever growing networks. In this paper, we survey prior work on sparsity in deep learning and provide an extensive tutorial of sparsification for both inference and training. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice. Our work distills ideas from more than 300 research papers and provides guidance to practitioners who wish to utilize sparsity today, as well as to researchers whose goal is to push the frontier forward. We include the necessary background on mathematical methods in sparsification, describe phenomena such as early structure adaptation, the intricate relations between sparsity and the training process, and show techniques for achieving acceleration on real hardware. We also define a metric of pruned parameter efficiency that could serve as a baseline for comparison of different sparse networks. We close by speculating on how sparsity can improve future workloads and outline major open problems in the field.

For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational efficiency). In this paper, we propose an efficient method to train a deep thin network with a theoretic guarantee. Our method is motivated by model compression. It consists of three stages. In the first stage, we sufficiently widen the deep thin network and train it until convergence. In the second stage, we use this well-trained deep wide network to warm up (or initialize) the original deep thin network. This is achieved by letting the thin network imitate the immediate outputs of the wide network from layer to layer. In the last stage, we further fine tune this well initialized deep thin network. The theoretical guarantee is established by using mean field analysis, which shows the advantage of layerwise imitation over traditional training deep thin networks from scratch by backpropagation. We also conduct large-scale empirical experiments to validate our approach. By training with our method, ResNet50 can outperform ResNet101, and BERT_BASE can be comparable with BERT_LARGE, where both the latter models are trained via the standard training procedures as in the literature.

Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement pooling operations that aggregate nodes belonging to the same cluster. However, the eigendecomposition of the Laplacian is expensive and, since clustering results are graph-specific, pooling methods based on SC must perform a new optimization for each new sample. In this paper, we propose a graph clustering approach that addresses these limitations of SC. We formulate a continuous relaxation of the normalized minCUT problem and train a GNN to compute cluster assignments that minimize this objective. Our GNN-based implementation is differentiable, does not require to compute the spectral decomposition, and learns a clustering function that can be quickly evaluated on out-of-sample graphs. From the proposed clustering method, we design a graph pooling operator that overcomes some important limitations of state-of-the-art graph pooling techniques and achieves the best performance in several supervised and unsupervised tasks.