数据剪辑对于降低量化操作中的噪声和提高量化感知训练（QAT）的准确性至关重要。当前的实践依靠启发式方法来设置剪接阈值标量，不能证明是最佳的。我们提出了最佳的剪切张量和向量（octav），这是一种递归算法，以确定MSE最佳的剪切标量。 OCTAV源自Fast Newton-Raphson方法，在QAT例程的每一个迭代中，都可以随时发现最佳的剪切标量。因此，QAT算法在每个步骤中都具有可证明的最小量化噪声配制。此外，我们揭示了QAT中常见梯度估计技术的局限性，并提出了幅度感知的分化，以进一步提高准确性。在实验上，启用了八度的QAT在多个任务上实现了最先进的精度。其中包括在ImageNet上进行训练，并在ImageNet上进行重新注册和Mobilenets，以及使用BERT模型进行微调，其中启用八叶速度的QAT始终以低精度（4到6位）保持准确性。我们的结果不需要对基线训练配方进行任何修改，除了在适当的情况下插入量化操作。

Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD are redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy during this compression, DGC employs four methods: momentum correction, local gradient clipping, momentum factor masking, and warm-up training. We have applied Deep Gradient Compression to image classification, speech recognition, and language modeling with multiple datasets including Cifar10, ImageNet, Penn Treebank, and Librispeech Corpus. On these scenarios, Deep Gradient Compression achieves a gradient compression ratio from 270× to 600× without losing accuracy, cutting the gradient size of ResNet-50 from 97MB to 0.35MB, and for DeepSpeech from 488MB to 0.74MB. Deep gradient compression enables large-scale distributed training on inexpensive commodity 1Gbps Ethernet and facilitates distributed training on mobile. The code is available at: https://github.com/synxlin/ deep-gradient-compression.

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets. While custom hardware helps the computation, fetching weights from DRAM is two orders of magnitude more expensive than ALU operations, and dominates the required power.Previously proposed 'Deep Compression' makes it possible to fit large DNNs (AlexNet and VGGNet) fully in on-chip SRAM. This compression is achieved by pruning the redundant connections and having multiple connections share the same weight. We propose an energy efficient inference engine (EIE) that performs inference on this compressed network model and accelerates the resulting sparse matrix-vector multiplication with weight sharing. Going from DRAM to SRAM gives EIE 120× energy saving; Exploiting sparsity saves 10×; Weight sharing gives 8×; Skipping zero activations from ReLU saves another 3×. Evaluated on nine DNN benchmarks, EIE is 189× and 13× faster when compared to CPU and GPU implementations of the same DNN without compression. EIE has a processing power of 102 GOPS/s working directly on a compressed network, corresponding to 3 TOPS/s on an uncompressed network, and processes FC layers of AlexNet at 1.88×10 4 frames/sec with a power dissipation of only 600mW. It is 24,000× and 3,400× more energy efficient than a CPU and GPU respectively. Compared with DaDianNao, EIE has 2.9×, 19× and 3× better throughput, energy efficiency and area efficiency.

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.

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the architecture. To address these limitations, we describe a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections. Our method prunes redundant connections using a three-step method. First, we train the network to learn which connections are important. Next, we prune the unimportant connections. Finally, we retrain the network to fine tune the weights of the remaining connections. On the ImageNet dataset, our method reduced the number of parameters of AlexNet by a factor of 9×, from 61 million to 6.7 million, without incurring accuracy loss. Similar experiments with VGG-16 found that the total number of parameters can be reduced by 13×, from 138 million to 10.3 million, again with no loss of accuracy.

Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts, but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this manuscript, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them to their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find average performance improvements of 4.2% across model complexities and prediction tasks, with substantial performance improvements of up to 16.4% in some cases. Furthermore, we find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.

Objective: We aim to develop an open-source natural language processing (NLP) package, SODA (i.e., SOcial DeterminAnts), with pre-trained transformer models to extract social determinants of health (SDoH) for cancer patients, examine the generalizability of SODA to a new disease domain (i.e., opioid use), and evaluate the extraction rate of SDoH using cancer populations. Methods: We identified SDoH categories and attributes and developed an SDoH corpus using clinical notes from a general cancer cohort. We compared four transformer-based NLP models to extract SDoH, examined the generalizability of NLP models to a cohort of patients prescribed with opioids, and explored customization strategies to improve performance. We applied the best NLP model to extract 19 categories of SDoH from the breast (n=7,971), lung (n=11,804), and colorectal cancer (n=6,240) cohorts. Results and Conclusion: We developed a corpus of 629 cancer patients notes with annotations of 13,193 SDoH concepts/attributes from 19 categories of SDoH. The Bidirectional Encoder Representations from Transformers (BERT) model achieved the best strict/lenient F1 scores of 0.9216 and 0.9441 for SDoH concept extraction, 0.9617 and 0.9626 for linking attributes to SDoH concepts. Fine-tuning the NLP models using new annotations from opioid use patients improved the strict/lenient F1 scores from 0.8172/0.8502 to 0.8312/0.8679. The extraction rates among 19 categories of SDoH varied greatly, where 10 SDoH could be extracted from >70% of cancer patients, but 9 SDoH had a low extraction rate (<70% of cancer patients). The SODA package with pre-trained transformer models is publicly available at https://github.com/uf-hobiinformatics-lab/SDoH_SODA.

我们提出了连续表示的时间扩展变化，我们称其为t-SR。 T-SR通过在原始动作重复序列上构造后继表示，捕获了时间扩展动作的预期状态过渡动力学。这种时间抽象的这种形式不能学习相关任务结构的自上而下的层次结构，而是对耦合动作和动作重复的自下而上的组成。这减少了在没有学习层次政策的情况下控制中所需的决策数量。因此，T-SR直接考虑了时间扩展的动作序列的时间范围，而无需预定义或域特异性选项。我们表明，在具有动态奖励结构的环境中，T-SR能够利用后继表示的灵活性和时间扩展的动作提供的抽象。因此，在一系列稀疏的网格世界环境中，T-SR最佳地适应策略远比基于可比的无模型的强化学习方法快得多。我们还表明，T-SR学到的解决这些任务的方式要求学习的策略的始终如一的频率比非临时扩展的策略少。

相干显微镜技术提供了跨科学和技术领域的材料的无与伦比的多尺度视图，从结构材料到量子设备，从综合电路到生物细胞。在构造更明亮的来源和高速探测器的驱动下，连贯的X射线显微镜方法（如Ptychography）有望彻底改变纳米级材料的特征。但是，相关的数据和计算需求显着增加意味着，常规方法不再足以从高速相干成像实验实时恢复样品图像。在这里，我们演示了一个工作流程，该工作流利用边缘的人工智能和高性能计算，以实现直接从检测器直接从检测器流出的X射线ptychography数据实时反演。拟议的AI支持的工作流程消除了传统的Ptychography施加的采样约束，从而使用比传统方法所需的数据较少的数据级允许低剂量成像。