Related papers: Fast Data Aware Neural Architecture Search via Sup…

The explosion of IoT sensors in industrial, consumer and remote sensing use cases has come with unprecedented demand for computing infrastructure to transmit and to analyze petabytes of data. Concurrently, the world is slowly shifting its…

The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data…

Data scientists seeking a good supervised learning model on a new dataset have many choices to make: they must preprocess the data, select features, possibly reduce the dimension, select an estimation algorithm, and choose hyperparameters…

Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…

Machine Learning (ML) systems are increasingly used to support decision-making processes that affect individuals. However, these systems often rely on biased data, which can lead to unfair outcomes against specific groups. With the growing…

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

The demand for a huge amount of data for machine learning (ML) applications is currently a bottleneck in an empirically dominated field. We propose a method to combine prior knowledge with data-driven methods to significantly reduce their…

The field of Automatic Machine Learning (AutoML) has recently attained impressive results, including the discovery of state-of-the-art machine learning solutions, such as neural image classifiers. This is often done by applying an…

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware…

A rising research challenge is running costly machine learning (ML) networks locally on resource-constrained edge devices. ML networks with large convolutional layers can easily exceed available memory, increasing latency due to excessive…

Modern day computing increasingly relies on specialization to satiate growing performance and efficiency requirements. A core challenge in designing such specialized hardware architectures is how to perform mapping space search, i.e.,…

Hardware-aware neural architecture designs have been predominantly focusing on optimizing model performance on single hardware and model development complexity, where another important factor, model deployment complexity, has been largely…

Anomaly detection plays a key role in industrial quality control, where defects must be identified despite the scarcity of labeled faulty samples. Recent self-supervised approaches, such as GLASS, learn normal visual patterns using only…

Monitoring and detecting abnormal events in cyber-physical systems is crucial to industrial production. With the prevalent deployment of the Industrial Internet of Things (IIoT), an enormous amount of time series data is collected to…

The practical application of AI tools for specific computer vision tasks relies on the "small-data regime" of hundreds to thousands of labeled samples. This small-data regime is vital for applications requiring expensive expert annotations,…

Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed…

Small-scale farming communities are disproportionately affected by water scarcity, erratic climate patterns, and a lack of access to advanced, affordable agricultural technologies. To address these challenges, this paper presents a novel,…

To mitigate the pain of manually tuning hyperparameters of deep neural networks, automated machine learning (AutoML) methods have been developed to search for an optimal set of hyperparameters in large combinatorial search spaces. However,…

Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful techniques for tackling…

Search space design is very critical to neural architecture search (NAS) algorithms. We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in recent NAS algorithms.…