Related papers: Accelerator-Oriented Algorithm Transformation for …
FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, including…
Recently, Deep Neural Networks (DNNs) have recorded great success in handling medical and other complex classification tasks. However, as the sizes of a DNN model and the available dataset increase, the training process becomes more complex…
We propose a new objective for option discovery that emphasizes the computational advantage of using options in planning. In a sequential machine, the speed of planning is proportional to the number of elementary operations used to achieve…
Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully…
The ability to train large-scale neural networks has resulted in state-of-the-art performance in many areas of computer vision. These results have largely come from computational break throughs of two forms: model parallelism, e.g. GPU…
Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…
There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural…
Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that…
The increasing complexity of the software/hardware stack of modern supercomputers results in explosion of parameters. The performance analysis becomes a truly experimental science, even more challenging in the presence of massive…
Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…
Advancements in AI have greatly enhanced the medical imaging process, making it quicker to diagnose patients. However, very few have investigated the optimization of a multi-model system with hardware acceleration. As specialized edge…
Efficient Graph processing is challenging because of the irregularity of graph algorithms. Using GPUs to accelerate irregular graph algorithms is even more difficult to be efficient, since GPU's highly structured SIMT architecture is not a…
While Transformers have revolutionized machine learning on various data, existing Transformers for temporal graphs face limitations in (1) restricted receptive fields, (2) overhead of subgraph extraction, and (3) suboptimal generalization…
Planning long-horizon robot manipulation requires making discrete decisions about which objects to interact with and continuous decisions about how to interact with them. A robot planner must select grasps, placements, and motions that are…
In order to satisfy timing constraints, modern real-time applications require massively parallel accelerators such as General Purpose Graphic Processing Units (GPGPUs). Generation after generation, the number of computing clusters made…
Accurate hardware performance models are critical to efficient code generation. They can be used by compilers to make heuristic decisions, by superoptimizers as a minimization objective, or by autotuners to find an optimal configuration for…
Hyperparameter selection in continual learning scenarios is a challenging and underexplored aspect, especially in practical non-stationary environments. Traditional approaches, such as grid searches with held-out validation data from all…
Motivation: Several different threads of research have been proposed for modeling and mining temporal data. On the one hand, approaches such as dynamic Bayesian networks (DBNs) provide a formal probabilistic basis to model relationships…
Episode discovery from an event is a popular framework for data mining tasks and has many real-world applications. An episode is a partially ordered set of objects (e.g., item, node), and each object is associated with an event type. This…
While anomaly detection in time series has been an active area of research for several years, most recent approaches employ an inadequate evaluation criterion leading to an inflated F1 score. We show that a rudimentary Random Guess method…