1. Joint Species Distribution models (JSDMs) explain spatial variation in community composition by contributions of the environment, biotic associations, and possibly spatially structured residual covariance. They show great promise as a general analytical framework for community ecology and macroecology, but current JSDMs, even when approximated by latent variables, scale poorly on large datasets, limiting their usefulness for currently emerging big (e.g., metabarcoding and metagenomics) community datasets. 2. Here, we present a novel, more scalable JSDM (sjSDM) that circumvents the need to use latent variables by using a Monte-Carlo integration of the joint JSDM likelihood and allows flexible elastic net regularization on all model components. We implemented sjSDM in PyTorch, a modern machine learning framework that can make use of CPU and GPU calculations. Using simulated communities with known species-species associations and different number of species and sites, we compare sjSDM with state-of-the-art JSDM implementations to determine computational runtimes and accuracy of the inferred species-species and species-environmental associations. 3. We find that sjSDM is orders of magnitude faster than existing JSDM algorithms (even when run on the CPU) and can be scaled to very large datasets. Despite the dramatically improved speed, sjSDM produces more accurate estimates of species association structures than alternative JSDM implementations. We demonstrate the applicability of sjSDM to big community data using eDNA case study with thousands of fungi operational taxonomic units (OTU). 4. Our sjSDM approach makes the analysis of JSDMs to large community datasets with hundreds or thousands of species possible, substantially extending the applicability of JSDMs in ecology. We provide our method in an R package to facilitate its applicability for practical data analysis.
Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks with compact models at various stages in the MRI workflow can significantly reduce the required storage space and provide considerable speedup. In computer vision, knowledge distillation is a commonly used method for model compression. In our work, we propose a knowledge distillation (KD) framework for the image to image problems in the MRI workflow in order to develop compact, low-parameter models without a significant drop in performance. We propose a combination of the attention-based feature distillation method and imitation loss and demonstrate its effectiveness on the popular MRI reconstruction architecture, DC-CNN. We conduct extensive experiments using Cardiac, Brain, and Knee MRI datasets for 4x, 5x and 8x accelerations. We observed that the student network trained with the assistance of the teacher using our proposed KD framework provided significant improvement over the student network trained without assistance across all the datasets and acceleration factors. Specifically, for the Knee dataset, the student network achieves $65\%$ parameter reduction, 2x faster CPU running time, and 1.5x faster GPU running time compared to the teacher. Furthermore, we compare our attention-based feature distillation method with other feature distillation methods. We also conduct an ablative study to understand the significance of attention-based distillation and imitation loss. We also extend our KD framework for MRI super-resolution and show encouraging results.
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, using two small and six large image classification models. Due to the limited memory of the edge device's TEE, we partition model layers into more sensitive layers (to be executed inside the device TEE), and a set of layers to be executed in the untrusted part of the operating system. Our results show that even if a single layer is hidden, we can provide reliable model privacy and defend against state of the art MIAs, with only 3% performance overhead. When fully utilizing the TEE, DarkneTZ provides model protections with up to 10% overhead.
Blockchain-enabled Federated Learning (BFL) enables mobile devices to collaboratively train neural network models required by a Machine Learning Model Owner (MLMO) while keeping data on the mobile devices. Then, the model updates are stored in the blockchain in a decentralized and reliable manner. However, the issue of BFL is that the mobile devices have energy and CPU constraints that may reduce the system lifetime and training efficiency. The other issue is that the training latency may increase due to the blockchain mining process. To address these issues, the MLMO needs to (i) decide how much data and energy that the mobile devices use for the training and (ii) determine the block generation rate to minimize the system latency, energy consumption, and incentive cost while achieving the target accuracy for the model. Under the uncertainty of the BFL environment, it is challenging for the MLMO to determine the optimal decisions. We propose to use the Deep Reinforcement Learning (DRL) to derive the optimal decisions for the MLMO.
With the recent trend of "network softwarisation", enabled by emerging technologies such as Software-Defined Networking (SDN) and Network Function Virtualisation (NFV), system administrators of data centres and enterprise networks have started replacing dedicated hardware-based middleboxes with virtualised network functions running on servers and end hosts. This radical change has facilitated the provisioning of advanced and flexible network services, ultimately helping system administrators and network operators to cope with the rapid changes in service requirements and networking workloads. This thesis investigates the challenges of provisioning network security services in "softwarised" networks, where the security of residential and business users can be provided by means of sets of software-based network functions running on high performance servers or on commodity compute devices. The study is approached from the perspective of the telecom operator, whose goal is to protect the customers from network threats and, at the same time, maximize the number of provisioned services, and thereby revenue. Specifically, the overall aim of the research presented in this thesis is proposing novel techniques for optimising the resource usage of software-based security services, hence for increasing the chances for the operator to accommodate more service requests while respecting the desired level of network security of its customers. In this direction, the contributions of this thesis are the following: (i) a solution for the dynamic provisioning of security services that minimises the utilisation of computing and network resources, and (ii) novel methods based on Deep Learning and Linux kernel technologies for reducing the CPU usage of software-based security network functions, with specific focus on the defence against Distributed Denial of Service (DDoS) attacks.
With more and more event-based neuromorphic hardware systems being developed at universities and in industry, there is a growing need for assessing their performance with domain specific measures. In this work, we use the methodology of converting pre-trained non-spiking to spiking neural networks to evaluate the performance loss and measure the energy-per-inference for three neuromorphic hardware systems (BrainScaleS, Spikey, SpiNNaker) and common simulation frameworks for CPU (NEST) and CPU/GPU (GeNN). For analog hardware we further apply a re-training technique known as hardware-in-the-loop training to cope with device mismatch. This analysis is performed for five different networks, including three networks that have been found by an automated optimization with a neural architecture search framework. We demonstrate that the conversion loss is usually below one percent for digital implementations, and moderately higher for analog systems with the benefit of much lower energy-per-inference costs.
Deep learning techniques are currently the state of the art approach to deal with image classification problems. Nevertheless, non-expert users might find challenging the use of these techniques due to several reasons, including the lack of enough images, the necessity of trying different models and conducting a thorough comparison of the results obtained with them, and the technical difficulties of employing different libraries, tools and special purpose hardware like GPUs. In this work, we present FrImCla, an open-source and free tool that simplifies the construction of robust models for image classification from a dataset of images, and only using the computer CPU. Given a dataset of annotated images, FrImCla automatically constructs a classification model (both for single-label and multi-label classification problems) by trying several feature extractors (based both on transfer learning and traditional computer vision methods) and machine learning algorithms, and selecting the best combination after a thorough statistical analysis. Thus, this tool can be employed by non-expert users to create accurate models from small datasets of images without requiring any special purpose hardware. In addition, in this paper, we show that FrImCla can be employed to construct accurate models that are close, or even better, to the state-of-the-art models.
The main flaw of neural network ensembling is that it is exceptionally demanding computationally, especially, if the individual sub-models are large neural networks, which must be trained separately. Having in mind that modern DNNs can be very accurate, they are already the huge ensembles of simple classifiers, and that one can construct more thrifty compressed neural net of a similar performance for any ensemble, the idea of designing the expensive SuperNets can be questionable. The widespread belief that ensembling increases the prediction time, makes it not attractive and can be the reason that the main stream of ML research is directed towards developing better loss functions and learning strategies for more advanced and efficient neural networks. On the other hand, all these factors make the architectures more complex what may lead to overfitting and high computational complexity, that is, to the same flaws for which the highly parametrized SuperNets ensembles are blamed. The goal of the master thesis is to speed up the execution time required for ensemble generation. Instead of training K inaccurate sub-models, each of them can represent various phases of training (representing various local minima of the loss function) of a single DNN [Huang et al., 2017; Gripov et al., 2018]. Thus, the computational performance of the SuperNet can be comparable to the maximum CPU time spent on training its single sub-model, plus usually much shorter CPU time required for training the SuperNet coupling factors.
The recent introduction of powerful embedded graphics processing units (GPUs) has allowed for unforeseen improvements in real-time computer vision applications. It has enabled algorithms to run onboard, well above the standard video rates, yielding not only higher information processing capability, but also reduced latency. This work focuses on the applicability of efficient low-level, GPU hardware-specific instructions to improve on existing computer vision algorithms in the field of visual-inertial odometry (VIO). While most steps of a VIO pipeline work on visual features, they rely on image data for detection and tracking, of which both steps are well suited for parallelization. Especially non-maxima suppression and the subsequent feature selection are prominent contributors to the overall image processing latency. Our work first revisits the problem of non-maxima suppression for feature detection specifically on GPUs, and proposes a solution that selects local response maxima, imposes spatial feature distribution, and extracts features simultaneously. Our second contribution introduces an enhanced FAST feature detector that applies the aforementioned non-maxima suppression method. Finally, we compare our method to other state-of-the-art CPU and GPU implementations, where we always outperform all of them in feature tracking and detection, resulting in over 1000fps throughput on an embedded Jetson TX2 platform. Additionally, we demonstrate our work integrated in a VIO pipeline achieving a metric state estimation at ~200fps.
Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of correlation filters. However, predefined parameters introduce much effort in tuning them and they still fail to adapt to new situations that the designer did not think of. In this work, a novel approach is proposed to online automatically and adaptively learn spatio-temporal regularization term. Spatially local response map variation is introduced as spatial regularization to make DCF focus on the learning of trust-worthy parts of the object, and global response map variation determines the updating rate of the filter. Extensive experiments on four UAV benchmarks have proven the superiority of our method compared to the state-of-the-art CPU- and GPU-based trackers, with a speed of ~60 frames per second running on a single CPU. Our tracker is additionally proposed to be applied in UAV localization. Considerable tests in the indoor practical scenarios have proven the effectiveness and versatility of our localization method. The code is available at https://github.com/vision4robotics/AutoTrack.
Automatic Speech Recognition (ASR) has increased in popularity in recent years. The evolution of processor and storage technologies has enabled more advanced ASR mechanisms, fueling the development of virtual assistants such as Amazon Alexa, Apple Siri, Microsoft Cortana, and Google Home. The interest in such assistants, in turn, has amplified the novel developments in ASR research. However, despite this popularity, there has not been a detailed training efficiency analysis of modern ASR systems. This mainly stems from: the proprietary nature of many modern applications that depend on ASR, like the ones listed above; the relatively expensive co-processor hardware that is used to accelerate ASR by big vendors to enable such applications; and the absence of well-established benchmarks. The goal of this paper is to address the latter two of these challenges. The paper first describes an ASR model, based on a deep neural network inspired by recent work in this domain, and our experiences building it. Then we evaluate this model on three CPU-GPU co-processor platforms that represent different budget categories. Our results demonstrate that utilizing hardware acceleration yields good results even without high-end equipment. While the most expensive platform (10X price of the least expensive one) converges to the initial accuracy target 10-30% and 60-70% faster than the other two, the differences among the platforms almost disappear at slightly higher accuracy targets. In addition, our results further highlight both the difficulty of evaluating ASR systems due to the complex, long, and resource intensive nature of the model training in this domain, and the importance of establishing benchmarks for ASR.
The MAX-MIN Ant System (MMAS) is one of the best-known Ant Colony Optimization (ACO) algorithms proven to be efficient at finding satisfactory solutions to many difficult combinatorial optimization problems. The slow-down in Moore's law, and the availability of graphics processing units (GPUs) capable of conducting general-purpose computations at high speed, has sparked considerable research efforts into the development of GPU-based ACO implementations. In this paper, we discuss a range of novel ideas for improving the GPU-based parallel MMAS implementation, allowing it to better utilize the computing power offered by two subsequent Nvidia GPU architectures. Specifically, based on the weighted reservoir sampling algorithm we propose a novel parallel implementation of the node selection procedure, which is at the heart of the MMAS and other ACO algorithms. We also present a memory-efficient implementation of another key-component -- the tabu list structure -- which is used in the ACO's solution construction stage. The proposed implementations, combined with the existing approaches, lead to a total of six MMAS variants, which are evaluated on a set of Traveling Salesman Problem (TSP) instances ranging from 198 to 3,795 cities. The results show that our MMAS implementation is competitive with state-of-the-art GPU-based and multi-core CPU-based parallel ACO implementations: in fact, the times obtained for the Nvidia V100 Volta GPU were up to 7.18x and 21.79x smaller, respectively. The fastest of the proposed MMAS variants is able to generate over 1 million candidate solutions per second when solving a 1,002-city instance. Moreover, we show that, combined with the 2-opt local search heuristic, the proposed parallel MMAS finds high-quality solutions for the TSP instances with up to 18,512 nodes.
For vehicles equipped with the automatic parking system, the accuracy and speed of the parking slot detection are crucial. But the high accuracy is obtained at the price of low speed or expensive computation equipment, which are sensitive for many car manufacturers. In this paper, we proposed a detector using CNN(convolutional neural networks) for faster speed and smaller model size while keeps accuracy. To achieve the optimal balance, we developed a strategy to select the best receptive fields and prune the redundant channels automatically after each training epoch. The proposed model is capable of jointly detecting corners and line features of parking slots while running efficiently in real time on average processors. The model has a frame rate of about 30 FPS on a 2.3 GHz CPU core, yielding parking slot corner localization error of 1.51$\pm$2.14 cm (std. err.) and slot detection accuracy of 98\%, generally satisfying the requirements in both speed and accuracy on on-board mobile terminals.
A pivotal step in image super-resolution techniques is interpolation, which aims at generating high resolution images without introducing artifacts such as blurring and ringing. In this paper, we propose a technique that performs interpolation through an infusion of high frequency signal components computed by exploiting `process similarity'. By `process similarity', we refer to the resemblance between a decomposition of the image at a resolution to the decomposition of the image at another resolution. In our approach, the decompositions generating image details and approximations are obtained through the discrete wavelet (DWT) and stationary wavelet (SWT) transforms. The complementary nature of DWT and SWT is leveraged to get the structural relation between the input image and its low resolution approximation. The structural relation is represented by optimal model parameters obtained through particle swarm optimization (PSO). Owing to process similarity, these parameters are used to generate the high resolution output image from the input image. The proposed approach is compared with six existing techniques qualitatively and in terms of PSNR, SSIM, and FSIM measures, along with computation time (CPU time). It is found that our approach is the fastest in terms of CPU time and produces comparable results.
Motivation: We introduce SneakySnake, a highly parallel and highly accurate pre-alignment filter that remarkably reduces the need for computationally costly sequence alignment. The key idea of SneakySnake is to reduce the approximate string matching (ASM) problem to the single net routing (SNR) problem in VLSI chip layout. In the SNR problem, we are interested in finding the optimal path that connects two terminals with the least routing cost on a special grid layout that contains obstacles. The SneakySnake algorithm quickly solves the SNR problem and uses the found optimal path to decide whether or not performing sequence alignment is necessary. Reducing the ASM problem into SNR also makes SneakySnake efficient to implement on CPUs, GPUs, and FPGAs. Results: SneakySnake significantly improves the accuracy of pre-alignment filtering by up to four orders of magnitude compared to the state-of-the-art pre-alignment filters, Shouji, GateKeeper, and SHD. For short sequences, SneakySnake accelerates Edlib (state-of-the-art implementation of Myers's bit-vector algorithm) and Parasail (state-of-the-art sequence aligner with a configurable scoring function), by up to 37.7x and 43.9x (>12x on average), respectively, with its CPU implementation, and by up to 413x and 689x (>400x on average), respectively, with FPGA and GPU acceleration. For long sequences, the CPU implementation of SneakySnake accelerates Parasail and KSW2 (sequence aligner of minimap2) by up to 979x (276.9x on average) and 91.7x (31.7x on average), respectively. As SneakySnake does not replace sequence alignment, users can still obtain all capabilities (e.g., configurable scoring functions) of the aligner of their choice, unlike existing acceleration efforts that sacrifice some aligner capabilities. Availability: https://github.com/CMU-SAFARI/SneakySnake
Deploying big-data Machine Learning (ML) services in a cloud environment presents a challenge to the cloud vendor with respect to the cloud container configuration sizing for any given customer use case. OracleLabs has developed an automated framework that uses nested-loop Monte Carlo simulation to autonomously scale any size customer ML use cases across the range of cloud CPU-GPU "Shapes" (configurations of CPUs and/or GPUs in Cloud containers available to end customers). Moreover, the OracleLabs and NVIDIA authors have collaborated on a ML benchmark study which analyzes the compute cost and GPU acceleration of any ML prognostic algorithm and assesses the reduction of compute cost in a cloud container comprising conventional CPUs and NVIDIA GPUs.
The segmentation and analysis of coronary arteries from intravascular optical coherence tomography (IVOCT) is an important aspect of diagnosing and managing coronary artery disease. Current image processing methods are hindered by the time needed to generate expert-labelled datasets and the potential for bias during the analysis. Therefore, automated, robust, unbiased and timely geometry extraction from IVOCT, using image processing, would be beneficial to clinicians. With clinical application in mind, we aim to develop a model with a small memory footprint that is fast at inference time without sacrificing segmentation quality. Using a large IVOCT dataset of 12,011 expert-labelled images from 22 patients, we construct a new deep learning method based on capsules which automatically produces lumen segmentations. Our dataset contains images with both blood and light artefacts (22.8%), as well as metallic (23.1%) and bioresorbable stents (2.5%). We split the dataset into a training (70%), validation (20%) and test (10%) set and rigorously investigate design variations with respect to upsampling regimes and input selection. We show that our developments lead to a model, DeepCap, that is on par with state-of-the-art machine learning methods in terms of segmentation quality and robustness, while using as little as 12% of the parameters. This enables DeepCap to have per image inference times up to 70% faster on GPU and up to 95% faster on CPU compared to other state-of-the-art models. DeepCap is a robust automated segmentation tool that can aid clinicians to extract unbiased geometrical data from IVOCT.
The Frank-Wolfe algorithm has become a popular first-order optimization algorithm for it is simple and projection-free, and it has been successfully applied to a variety of real-world problems. Its main drawback however lies in its convergence rate, which can be excessively slow due to naive descent directions. We propose to speed up the Frank-Wolfe algorithm by better aligning the descent direction with that of the negative gradient via a subroutine. This subroutine chases the negative gradient direction in a matching pursuit-style while still preserving the projection-free property. Although the approach is reasonably natural, it produces very significant results. We derive convergence rates $\mathcal{O}(1/t)$ to $\mathcal{O}(e^{-\omega t})$ of our method and we demonstrate its competitive advantage both per iteration and in CPU time over the state-of-the-art in a series of computational experiments.
Neural networks of ads systems usually take input from multiple resources, e.g., query-ad relevance, ad features and user portraits. These inputs are encoded into one-hot or multi-hot binary features, with typically only a tiny fraction of nonzero feature values per example. Deep learning models in online advertising industries can have terabyte-scale parameters that do not fit in the GPU memory nor the CPU main memory on a computing node. For example, a sponsored online advertising system can contain more than $10^{11}$ sparse features, making the neural network a massive model with around 10 TB parameters. In this paper, we introduce a distributed GPU hierarchical parameter server for massive scale deep learning ads systems. We propose a hierarchical workflow that utilizes GPU High-Bandwidth Memory, CPU main memory and SSD as 3-layer hierarchical storage. All the neural network training computations are contained in GPUs. Extensive experiments on real-world data confirm the effectiveness and the scalability of the proposed system. A 4-node hierarchical GPU parameter server can train a model more than 2X faster than a 150-node in-memory distributed parameter server in an MPI cluster. In addition, the price-performance ratio of our proposed system is 4-9 times better than an MPI-cluster solution.
Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability. In this work, a novel time slot-based distillation approach is proposed to efficiently and effectively optimize the training-set's quality on the fly. A cooperative energy minimization function is established to score the historical samples adaptively. To accelerate the scoring process, frames with high confident tracking results are employed as the keyframes to divide the tracking process into multiple time slots. After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored. Besides, when the current time slot exceeds the maximum frame number, which can be scored, the sample with the lowest score will be discarded. Consequently, the training-set can be efficiently and reliably distilled. Comprehensive tests on two well-known UAV benchmarks prove the effectiveness of our method with real-time speed on a single CPU.