Related papers: MRCN: Enhanced Coherence Mechanism for Near Memory…
Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory…
Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world…
Modern warehouse-scale datacenters commonly collocate multiple jobs on shared machines to improve resource utilization. However, such collocation often leads to performance interference caused by antagonistic jobs that overconsume shared…
The CP decomposition for high dimensional non-orthogonal spiked tensors is an important problem with broad applications across many disciplines. However, previous works with theoretical guarantee typically assume restrictive incoherence…
The electromagnetic inverse scattering problem (ISP), due to its inherent strong nonlinearity and severe ill-posedness, has long been a core challenge in microwave imaging. In recent years, physics-informed neural networks (PINNs) have…
Hardware implementations of Spiking Neural Networks (SNNs) represent a promising approach to edge-computing for applications that require low-power and low-latency, and which cannot resort to external cloud-based computing services.…
In-Memory Computing (IMC) introduces a new paradigm of computation that offers high efficiency in terms of latency and power consumption for AI accelerators. However, the non-idealities and defects of emerging technologies used in advanced…
In distributed ML applications, shared parameters are usually replicated among computing nodes to minimize network overhead. Therefore, proper consistency model must be carefully chosen to ensure algorithm's correctness and provide high…
Big datasets are gathered daily from different remote sensing platforms. Recently, statistical co-kriging models, with the help of scalable techniques, have been able to combine such datasets by using spatially varying bias corrections. The…
Longitudinal analysis has great potential to reveal developmental trajectories and monitor disease progression in medical imaging. This process relies on consistent and robust joint 4D segmentation. Traditional techniques are dependent on…
Robust trajectory optimization enables autonomous systems to operate safely under uncertainty by computing control policies that satisfy the constraints for all bounded disturbances. However, these problems often lead to large Second Order…
As transistor-based memory technologies like dynamic random access memory (DRAM) approach their scalability limits, the need to explore alternative storage solutions becomes increasingly urgent. Phase-change memory (PCM) has gained…
Planning problems in partially observable environments cannot be solved directly with convolutional networks and require some form of memory. But, even memory networks with sophisticated addressing schemes are unable to learn intelligent…
Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state…
Kinodynamic Motion Planning (KMP) is to find a robot motion subject to concurrent kinematics and dynamics constraints. To date, quite a few methods solve KMP problems and those that exist struggle to find near-optimal solutions and exhibit…
Fault tolerance is one of the major design goals for HPC. The emergence of non-volatile memories (NVM) provides a solution to build fault tolerant HPC. Data in NVM-based main memory are not lost when the system crashes because of the…
As Artificial Intelligence (AI) models are increasingly integrated into critical systems, the need for a robust framework to establish the trustworthiness of AI is increasingly paramount. While collaborative efforts have established…
Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagation through time, which entails unfolding the network over…
Controlling spacecraft near asteroids in deep space comes with many challenges. The delays involved necessitate heavy usage of limited onboard computation resources while fuel efficiency remains a priority to support the long loiter times…
De novo assembly enables investigations of unknown genomes, paving the way for personalized medicine and disease management. However, it faces immense computational challenges arising from the excessive data volumes and algorithmic…