Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference performance. Central to RecPipe is decomposing recommendation models into multi-stage pipelines to maintain quality while reducing compute complexity and exposing distinct parallelism opportunities. RecPipe implements an inference scheduler to map multi-stage recommendation engines onto commodity, heterogeneous platforms (e.g., CPUs, GPUs).While the hardware-aware scheduling improves ranking efficiency, the commodity platforms suffer from many limitations requiring specialized hardware. Thus, we design RecPipeAccel (RPAccel), a custom accelerator that jointly optimizes quality, tail-latency, and system throughput. RPAc-cel is designed specifically to exploit the distinct design space opened via RecPipe. In particular, RPAccel processes queries in sub-batches to pipeline recommendation stages, implements dual static and dynamic embedding caches, a set of top-k filtering units, and a reconfigurable systolic array. Com-pared to prior-art and at iso-quality, we demonstrate that RPAccel improves latency and throughput by 3x and 6x.

Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs). UAPs generalize across many different inputs; this leads to realistic and effective attacks that can be applied at scale. In this paper we propose HyperNeuron, an efficient and scalable algorithm that allows for the real-time detection of UAPs by identifying suspicious neuron hyper-activations. Our results show the effectiveness of HyperNeuron on multiple tasks (image classification, object detection), against a wide variety of universal attacks, and in realistic scenarios, like perceptual ad-blocking and adversarial patches. HyperNeuron is able to simultaneously detect both adversarial mask and patch UAPs with comparable or better performance than existing UAP defenses whilst introducing a significantly reduced latency of only 0.86 milliseconds per image. This suggests that many realistic and practical universal attacks can be reliably mitigated in real-time, which shows promise for the robust deployment of machine learning systems.

Pruning techniques for neural networks with a recurrent architecture, such as the recurrent neural network (RNN), are strongly desired for their application to edge-computing devices. However, the recurrent architecture is generally not robust to pruning because even small pruning causes accumulation error and the total error increases significantly over time. In this paper, we propose an appropriate pruning algorithm for RNNs inspired by "spectral pruning", and provide the generalization error bounds for compressed RNNs. We also provide numerical experiments to demonstrate our theoretical results and show the effectiveness of our pruning method compared with existing methods.

The learning rate (LR) schedule is one of the most important hyper-parameters needing careful tuning in training DNNs. However, it is also one of the least automated parts of machine learning systems and usually costs significant manual effort and computing. Though there are pre-defined LR schedules and optimizers with adaptive LR, they introduce new hyperparameters that need to be tuned separately for different tasks/datasets. In this paper, we consider the question: Can we automatically tune the LR over the course of training without human involvement? We propose an efficient method, AutoLRS, which automatically optimizes the LR for each training stage by modeling training dynamics. AutoLRS aims to find an LR applied to every $\tau$ steps that minimizes the resulted validation loss. We solve this black-box optimization on the fly by Bayesian optimization (BO). However, collecting training instances for BO requires a system to evaluate each LR queried by BO's acquisition function for $\tau$ steps, which is prohibitively expensive in practice. Instead, we apply each candidate LR for only $\tau'\ll\tau$ steps and train an exponential model to predict the validation loss after $\tau$ steps. This mutual-training process between BO and the loss-prediction model allows us to limit the training steps invested in the BO search. We demonstrate the advantages and the generality of AutoLRS through extensive experiments of training DNNs for tasks from diverse domains using different optimizers. The LR schedules auto-generated by AutoLRS lead to a speedup of $1.22\times$, $1.43\times$, and $1.5\times$ when training ResNet-50, Transformer, and BERT, respectively, compared to the LR schedules in their original papers, and an average speedup of $1.31\times$ over state-of-the-art heavily-tuned LR schedules.

Egocentric visual context detection can support intelligence augmentation applications. We created a wearable system, called PAL, for wearable, personalized, and privacy-preserving egocentric visual context detection. PAL has a wearable device with a camera, heart-rate sensor, on-device deep learning, and audio input/output. PAL also has a mobile/web application for personalized context labeling. We used on-device deep learning models for generic object and face detection, low-shot custom face and context recognition (e.g., activities like brushing teeth), and custom context clustering (e.g., indoor locations). The models had over 80\% accuracy in in-the-wild contexts (~1000 images) and we tested PAL for intelligence augmentation applications like behavior change. We have made PAL is open-source to further support intelligence augmentation using personalized and privacy-preserving egocentric visual contexts.

This paper aims to formulate the problem of estimating the optimal baseline values for the Shapley value in game theory. The Shapley value measures the attribution of each input variable of a complex model, which is computed as the marginal benefit from the presence of this variable w.r.t.its absence under different contexts. To this end, people usually set the input variable to its baseline value to represent the absence of this variable (i.e.the no-signal state of this variable). Previous studies usually determine the baseline values in an empirical manner, which hurts the trustworthiness of the Shapley value. In this paper, we revisit the feature representation of a deep model from the perspective of game theory, and define the multi-variate interaction patterns of input variables to define the no-signal state of an input variable. Based on the multi-variate interaction, we learn the optimal baseline value of each input variable. Experimental results have demonstrated the effectiveness of our method.

We present a general technique for constructing Graph Neural Networks (GNNs) capable of using multi-relational domain knowledge. The technique is based on mode-directed inverse entailment (MDIE) developed in Inductive Logic Programming (ILP). Given a data instance $e$ and background knowledge $B$, MDIE identifies a most-specific logical formula $\bot_B(e)$ that contains all the relational information in $B$ that is related to $e$. We transform $\bot_B(e)$ into a corresponding "bottom-graph" that can be processed for use by standard GNN implementations. This transformation allows a principled way of incorporating generic background knowledge into GNNs: we use the term `BotGNN' for this form of graph neural networks. For several GNN variants, using real-world datasets with substantial background knowledge, we show that BotGNNs perform significantly better than both GNNs without background knowledge and a recently proposed simplified technique for including domain knowledge into GNNs. We also provide experimental evidence comparing BotGNNs favourably to multi-layer perceptrons (MLPs) that use features representing a "propositionalised" form of the background knowledge; and BotGNNs to a standard ILP based on the use of most-specific clauses. Taken together, these results point to BotGNNs as capable of combining the computational efficacy of GNNs with the representational versatility of ILP.

Objective: To assess automatic computer-aided in-situ recognition of morphological features of pure and mixed urinary stones using intraoperative digital endoscopic images acquired in a clinical setting. Materials and methods: In this single-centre study, an experienced urologist intraoperatively and prospectively examined the surface and section of all kidney stones encountered. Calcium oxalate monohydrate (COM/Ia), dihydrate (COD/IIb) and uric acid (UA/IIIb) morphological criteria were collected and classified to generate annotated datasets. A deep convolutional neural network (CNN) was trained to predict the composition of both pure and mixed stones. To explain the predictions of the deep neural network model, coarse localisation heat-maps were plotted to pinpoint key areas identified by the network. Results: This study included 347 and 236 observations of stone surface and stone section, respectively. A highest sensitivity of 98 % was obtained for the type "pure IIIb/UA" using surface images. The most frequently encountered morphology was that of the type "pure Ia/COM"; it was correctly predicted in 91 % and 94 % of cases using surface and section images, respectively. Of the mixed type "Ia/COM+IIb/COD", Ia/COM was predicted in 84 % of cases using surface images, IIb/COD in 70 % of cases, and both in 65 % of cases. Concerning mixed Ia/COM+IIIb/UA stones, Ia/COM was predicted in 91 % of cases using section images, IIIb/UA in 69 % of cases, and both in 74 % of cases. Conclusions: This preliminary study demonstrates that deep convolutional neural networks are promising to identify kidney stone composition from endoscopic images acquired intraoperatively. Both pure and mixed stone composition could be discriminated. Collected in a clinical setting, surface and section images analysed by deep CNN provide valuable information about stone morphology for computer-aided diagnosis.

Between the rolled eyes, shrugged shoulders, jazzed hands and warbling vocal inflection, it's not hard to tell when someone's being sarcastic as they're giving you the business face to face. Online, however, you're going to need that SpongeBob meme and a liberal application of the shift key to get your contradictory point across. Lucky for us netizens, DARPA's Information Innovation Office (I2O) has collaborated with researchers from the University of Central Florida to develop a deep learning AI capable of understanding written sarcasm with a startling degree of accuracy. "With the high velocity and volume of social media data, companies rely on tools to analyze data and to provide customer service. These tools perform tasks such as content management, sentiment analysis, and extraction of relevant messages for the company's customer service representatives to respond to," UCF Associate Professor of Industrial Engineering and Management Systems, Dr. Ivan Garibay, told Engadget via email.

"The rise of innovation" in the Cloud has changed the way things used to work on the ground. The game-changing idea of Implementing DevOps with the cloud also pointed to a set of problems like application portability, security, etc. In the olden days, Companies wasted a large amount of capital and resources for maintaining and setting up oversized servers which sometimes used to run as 5–10% of its potential capacity. As a solution to this problem, a concept of "Virtualization" was introduced which presented the idea of isolating a dedicated guest OS to an application that is running over Host OS. VMs solved the problem of server capacity wastage to a greater extent as now we had a way of utilizing the spare capacity of a server in case of a new application.