Related papers: TinyOL: TinyML with Online-Learning on Microcontro…
Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first…
Always-on TinyML perception tasks in IoT applications require very high energy efficiency. Analog compute-in-memory (CiM) using non-volatile memory (NVM) promises high efficiency and also provides self-contained on-chip model storage.…
Monitoring biodiversity at scale is challenging. Detecting and identifying species in fine grained taxonomies requires highly accurate machine learning (ML) methods. Training such models requires large high quality data sets. And deploying…
Automated tuning of compute kernels is a popular area of research, mainly focused on finding optimal kernel parameters for a problem with fixed input sizes. This approach is good for deploying machine learning models, where the network…
The rapid development in ubiquitous computing has enabled the use of microcontrollers as edge devices. These devices are used to develop truly distributed IoT-based mechanisms where machine learning (ML) models are utilized. However,…
Deploying Machine learning (ML) on milliwatt-scale edge devices (tinyML) is gaining popularity due to recent breakthroughs in ML and Internet of Things (IoT). Most tinyML research focuses on model compression techniques that trade accuracy…
In recent years, the proliferation of unmanned aerial vehicles (UAVs) has increased dramatically. UAVs can accomplish complex or dangerous tasks in a reliable and cost-effective way but are still limited by power consumption problems, which…
The emergence and continued reliance on the Internet and related technologies has resulted in the generation of large amounts of data that can be made available for analyses. However, humans do not possess the cognitive capabilities to…
Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully…
Tiny machine learning (TinyML) co-locates models with sensors on microcontrollers, where small models (which are disproportionately sensitive to label noise) and bespoke binary tasks (which lack standard benchmarks) make general-purpose…
The Internet of Things (IoT) is an emerging technology that aims to connect heterogeneous and constrained objects to each other and to the Internet. It has grown significantly in a wide variety of applications such as smart homes, smart…
IoT devices based on microcontroller units (MCU) provide ultra-low power consumption and ubiquitous computation for near-sensor deep learning models (DNN). However, the memory of MCU is usually 2-3 orders of magnitude smaller than mobile…
While deep networks can learn complex functions such as classifiers, detectors, and trackers, many applications require models that continually adapt to changing input distributions, changing tasks, and changing environmental conditions.…
Continual learning enables AI systems to acquire new knowledge while retaining previously learned information. While traditional unimodal methods have made progress, the rise of Multimodal Large Language Models (MLLMs) brings new challenges…
The state-of-the-art online learning approaches are only capable of learning the metric for predefined tasks. In this paper, we consider lifelong learning problem to mimic "human learning", i.e., endowing a new capability to the learned…
Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various chart understanding tasks. However, the sheer size of these…
Machine learning algorithms have become indispensable in today's world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no…
Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has shown its effectiveness in online scenarios by continuously…
Automated machine learning techniques benefited from tremendous research progress in recently. These developments and the continuous-growing demand for machine learning experts led to the development of numerous AutoML tools. However, these…
In the wake of disruptive IoT technologies generating massive amounts of diverse data, Machine Learning (ML) will play a crucial role in bringing intelligence to Internet of Things (IoT) networks. This paper provides a comprehensive…