Related papers: A Tensor-Based Compiler and a Runtime for Neuron-L…
High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…
Deep Neural Networks (DNNs) have revolutionized many aspects of our lives. The use of DNNs is becoming ubiquitous including in softwares for image recognition, speech recognition, speech synthesis, language translation, to name a few. he…
In safety-critical systems (e.g., autonomous vehicles and robots), Deep Neural Networks (DNNs) are becoming a key component for computer vision tasks, particularly semantic segmentation. Further, since the DNN behavior cannot be assessed…
Graph classification is an important learning task for graph-structured data. Graph neural networks (GNNs) have recently gained growing attention in graph learning and have shown significant improvements in many important graph problems.…
While kernel methods and Graph Neural Networks offer complementary strengths, integrating the two has posed challenges in efficiency and scalability. The Graph Neural Tangent Kernel provides a theoretical bridge by interpreting GNNs through…
Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. This has generated significant interests in developing…
Computationally intensive deep neural networks (DNNs) are well-suited to run on GPUs, but newly developed algorithms usually require the heavily optimized DNN routines to work efficiently, and this problem could be even more difficult for…
Deep neural networks (DNNs) have demonstrated their outperformance in various domains. However, it raises a social concern whether DNNs can produce reliable and fair decisions especially when they are applied to sensitive domains involving…
Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model…
An accelerator is a specialized integrated circuit designed to perform specific computations faster than if those were performed by CPU or GPU. A Field-Programmable DNN learning and inference accelerator (FProg-DNN) using hybrid systolic…
Dynamic-shape deep neural networks (DNNs) are rapidly evolving, attracting attention for their ability to handle variable input sizes in real-time applications. However, existing compilation optimization methods for such networks often rely…
Despite significant investment in software infrastructure, machine learning systems, runtimes and compilers do not compose properly. We propose a new design aiming at providing unprecedented degrees of modularity, composability and…
Graph Neural Networks (GNNs) use a fully-connected layer to extract features from the nodes of a graph and aggregate these features using message passing between nodes, combining two distinct computational patterns: dense, regular…
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it is hardly used in the…
Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommendation. Despite the success of TGNNs, they are prone to the…
Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…
Tensor networks provide a powerful framework for compressing multi-dimensional data. The optimal tensor network structure for a given data tensor depends on both data characteristics and specific optimality criteria, making tensor network…
Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data. However, the current demand of DNNs for…
Sparse tensor algebra computations have become important in many real-world applications like machine learning, scientific simulations, and data mining. Hence, automated code generation and performance optimizations for tensor algebra…
Modern verification tools for deep neural networks (DNNs) increasingly rely on abstraction to scale to realistic architectures. In parallel, proof production is becoming a critical requirement for increasing the reliability of DNN…