Related papers: ACRoBat: Optimizing Auto-batching of Dynamic Deep …

In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an…

Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other…

As deep learning is pervasive in modern applications, many deep learning frameworks are presented for deep learning practitioners to develop and train DNN models rapidly. Meanwhile, as training large deep learning models becomes a trend in…

Autonomous drone navigation in dynamic environments remains a critical challenge, especially when dealing with unpredictable scenarios including fast-moving objects with rapidly changing goal positions. While traditional planners and…

Many hardware vendors have introduced specialized deep neural networks (DNN) accelerators owing to their superior performance and efficiency. As such, how to generate and optimize the code for the hardware accelerator becomes an important…

Autonomous driving requires reasoning about interactions with surrounding traffic. A prevailing approach is large-scale imitation learning on expert driving datasets, aimed at generalizing across diverse real-world scenarios. For online…

Dynamic graphs capture evolving interactions between entities, such as in social networks, online learning platforms, and crowdsourcing projects. For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream…

Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's hyperparameters in order to improve its performance. Several theoretical and empirical results have demonstrated the benefits of dynamically controlling…

We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM). Rather than attention with a fixed number of steps for each input image, the model learns to decide when to stop…

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…

In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control…

The delta-bar-delta algorithm is recognized as a learning rate adaptation technique that enhances the convergence speed of the training process in optimization by dynamically scheduling the learning rate based on the difference between the…

Control synthesis for continuously-parameterized families of quantum gates can enable critical advantages for mid-sized quantum computing applications in advance of fault-tolerance. We combine quantum optimal control with physics-informed…

The need for automated real-time visual systems in applications such as smart camera surveillance, smart environments, and drones necessitates the improvement of methods for visual active monitoring and control. Traditionally, the active…

Dynamic quantum circuits incorporate mid-circuit measurements and feed-forward operations originally intended to realize Quantum Error Correction. This paradigm has recently been utilized to prepare certain states and long-range entangling…

The computational requirements for training deep neural networks (DNNs) have grown to the point that it is now standard practice to parallelize training. Existing deep learning systems commonly use data or model parallelism, but…

Complex image processing and computer vision systems often consist of a processing pipeline of functional modules. We intend to replace parts or all of a target pipeline with deep neural networks to achieve benefits such as increased…

Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial…

As deep neural networks (DNNs) are increasingly deployed on edge devices, optimizing models for constrained computational resources is critical. Existing auto-pruning methods face challenges due to the diversity of DNN models, various…

Distributed stream processing systems are widely deployed to process real-time data generated by various devices, such as sensors and software systems. A key challenge in the system is overloading, which leads to an unstable system status…