Related papers: Improving Routability Prediction via NAS Using a S…
Network simulation is pivotal in network modeling, assisting with tasks ranging from capacity planning to performance estimation. Traditional approaches such as Discrete Event Simulation (DES) face limitations in terms of computational cost…
In one-shot NAS, sub-networks need to be searched from the supernet to meet different hardware constraints. However, the search cost is high and $N$ times of searches are needed for $N$ different constraints. In this work, we propose a…
Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally…
Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new tasks) and stability (preserving past knowledge). Neural…
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of…
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due…
One of the primary challenges impeding the progress of Neural Architecture Search (NAS) is its extensive reliance on exorbitant computational resources. NAS benchmarks aim to simulate runs of NAS experiments at zero cost, remediating the…
Artificial intelligence and machine learning models deployed on edge devices, e.g., for quality control in Additive Manufacturing (AM), are frequently small in size. Such models usually have to deliver highly accurate results within a short…
We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best…
As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique missing from incremental…
Structural re-parameterization (Rep) methods has achieved significant performance improvement on traditional convolutional network. Most current Rep methods rely on prior knowledge to select the reparameterization operations. However, the…
Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neural architecture Search(NAS) for each task to tackle this…
Among various sensors for assisted and autonomous driving systems, automotive radar has been considered as a robust and low-cost solution even in adverse weather or lighting conditions. With the recent development of radar technologies and…
The smoothing issue in graph learning leads to indistinguishable node representations, posing significant challenges for graph-related tasks. However, our experiments reveal that this problem can uncover underlying properties of node…
Trajectory prediction is an important task that involves modeling the indeterminate nature of traffic actors to forecast future trajectories given the observed trajectory sequences. However, current methods confine themselves to presumed…
Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating…
Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the knowledge from a given teacher model. Previous DaNAS methods…
Neural Architecture Search (NAS), aiming at automatically designing network architectures by machines, is hoped and expected to bring about a new revolution in machine learning. Despite these high expectation, the effectiveness and…
In this paper, we present a general and effective framework for Neural Architecture Search (NAS), named PredNAS. The motivation is that given a differentiable performance estimation function, we can directly optimize the architecture…
The best neural architecture for a given machine learning problem depends on many factors: not only the complexity and structure of the dataset, but also on resource constraints including latency, compute, energy consumption, etc. Neural…