Onur Cezmi Mutlu
YOU?
Author Swipe
View article: Processing-in-memory for genomics workloads
Processing-in-memory for genomics workloads Open
Low-cost, high-throughput DNA and RNA sequencing (HTS) data is the main workforce for the life sciences. Genome sequencing is now becoming a part of Predictive, Preventive, Personalized, and Participatory (termed 'P4') medicine. All genomi…
View article: FIESTA: Fisher Information-based Efficient Selective Test-time Adaptation
FIESTA: Fisher Information-based Efficient Selective Test-time Adaptation Open
Robust facial expression recognition in unconstrained, "in-the-wild" environments remains challenging due to significant domain shifts between training and testing distributions. Test-time adaptation (TTA) offers a promising solution by ad…
View article: Harmonia: A Multi-Agent Reinforcement Learning Approach to Data Placement and Migration in Hybrid Storage Systems
Harmonia: A Multi-Agent Reinforcement Learning Approach to Data Placement and Migration in Hybrid Storage Systems Open
Hybrid storage systems (HSS) integrate multiple storage devices with diverse characteristics to deliver high performance and capacity at low cost. The performance of an HSS highly depends on the effectiveness of two key policies: (1) the d…
View article: Ariadne: A Hotness-Aware and Size-Adaptive Compressed Swap Technique for Fast Application Relaunch and Reduced CPU Usage on Mobile Devices
Ariadne: A Hotness-Aware and Size-Adaptive Compressed Swap Technique for Fast Application Relaunch and Reduced CPU Usage on Mobile Devices Open
Growing application memory demands and concurrent usage are making mobile device memory scarce. When memory pressure is high, current mobile systems use a RAM-based compressed swap scheme (called ZRAM) to compress unused execution-related …
View article: Understanding RowHammer Under Reduced Refresh Latency: Experimental Analysis of Real DRAM Chips and Implications on Future Solutions
Understanding RowHammer Under Reduced Refresh Latency: Experimental Analysis of Real DRAM Chips and Implications on Future Solutions Open
RowHammer is a major read disturbance mechanism in DRAM where repeatedly accessing (hammering) a row of DRAM cells (DRAM row) induces bitflips in physically nearby DRAM rows (victim rows). To ensure robust DRAM operation, state-of-the-art …
View article: Proteus: Enabling High-Performance Processing-Using-DRAM with Dynamic Bit-Precision, Adaptive Data Representation, and Flexible Arithmetic
Proteus: Enabling High-Performance Processing-Using-DRAM with Dynamic Bit-Precision, Adaptive Data Representation, and Flexible Arithmetic Open
Processing-using-DRAM (PUD) is a paradigm where the analog operational properties of DRAM are used to perform bulk logic operations. While PUD promises high throughput at low energy and area cost, we uncover three limitations of existing P…
View article: BIMSA: accelerating long sequence alignment using processing-in-memory
BIMSA: accelerating long sequence alignment using processing-in-memory Open
Motivation Recent advances in sequencing technologies have stressed the critical role of sequence analysis algorithms and tools in genomics and healthcare research. In particular, sequence alignment is a fundamental building block in many …
View article: Ensemble Modeling of Multiple Physical Indicators to Dynamically Phenotype Autism Spectrum Disorder
Ensemble Modeling of Multiple Physical Indicators to Dynamically Phenotype Autism Spectrum Disorder Open
Early detection of autism, a neurodevelopmental disorder marked by social communication challenges, is crucial for timely intervention. Recent advancements have utilized naturalistic home videos captured via the mobile application GuessWha…
View article: SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems
SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems Open
Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To…
View article: Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos
Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos Open
The increasing variety and quantity of tagged multimedia content on a variety of online platforms offer a unique opportunity to advance the field of human action recognition. In this study, we utilize 283,582 unique, unlabeled TikTok video…
View article: An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System
An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System Open
Training machine learning (ML) algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from cos…
View article: TempT: Temporal consistency for Test-time adaptation
TempT: Temporal consistency for Test-time adaptation Open
We introduce Temporal consistency for Test-time adaptation (TempT) a novel method for test-time adaptation on videos through the use of temporal coherence of predictions across sequential frames as a self-supervision signal. TempT is an ap…
View article: Computer Vision Estimation of Emotion Reaction Intensity in the Wild
Computer Vision Estimation of Emotion Reaction Intensity in the Wild Open
Emotions play an essential role in human communication. Developing computer vision models for automatic recognition of emotion expression can aid in a variety of domains, including robotics, digital behavioral healthcare, and media analyti…
View article: Training and Profiling a Pediatric Facial Expression Classifier for Children on Mobile Devices: Machine Learning Study
Training and Profiling a Pediatric Facial Expression Classifier for Children on Mobile Devices: Machine Learning Study Open
Background Implementing automated facial expression recognition on mobile devices could provide an accessible diagnostic and therapeutic tool for those who struggle to recognize facial expressions, including children with developmental beh…
View article: The Classification of Abnormal Hand Movement to Aid in Autism Detection: Machine Learning Study
The Classification of Abnormal Hand Movement to Aid in Autism Detection: Machine Learning Study Open
Background A formal autism diagnosis can be an inefficient and lengthy process. Families may wait several months or longer before receiving a diagnosis for their child despite evidence that earlier intervention leads to better treatment ou…
View article: Classifying Autism Spectrum Disorder Using Emotion Features From Video Recordings (Preprint)
Classifying Autism Spectrum Disorder Using Emotion Features From Video Recordings (Preprint) Open
BACKGROUND Autism Spectrum Disorder (ASD) is a prevalent neurodevelopmental disorder encountered by 1 in 44 children in the United States of America. Autism patients face difficulty effectively communicating with peers, articulating feeli…
View article: Training and Profiling a Pediatric Facial Expression Classifier for Children on Mobile Devices: Machine Learning Study (Preprint)
Training and Profiling a Pediatric Facial Expression Classifier for Children on Mobile Devices: Machine Learning Study (Preprint) Open
BACKGROUND Implementing automated facial expression recognition on mobile devices could provide an accessible diagnostic and therapeutic tool for those who struggle to recognize facial expressions, including children with developmental be…
View article: Improved Digital Therapy for Developmental Pediatrics Using Domain-Specific Artificial Intelligence: Machine Learning Study
Improved Digital Therapy for Developmental Pediatrics Using Domain-Specific Artificial Intelligence: Machine Learning Study Open
Background Automated emotion classification could aid those who struggle to recognize emotions, including children with developmental behavioral conditions such as autism. However, most computer vision emotion recognition models are traine…
View article: Machine learning models using mobile game play accurately classify children with autism
Machine learning models using mobile game play accurately classify children with autism Open
Digitally-delivered healthcare is well suited to address current inequities in the delivery of care due to barriers of access to healthcare facilities. As the COVID-19 pandemic phases out, we have a unique opportunity to capitalize on the …
View article: Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study
Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study Open
A formal autism diagnosis can be an inefficient and lengthy process. Families may wait months or longer before receiving a diagnosis for their child despite evidence that earlier intervention leads to better treatment outcomes. Digital tec…
View article: Activity Recognition with Moving Cameras and Few Training Examples: Applications for Detection of Autism-Related Headbanging
Activity Recognition with Moving Cameras and Few Training Examples: Applications for Detection of Autism-Related Headbanging Open
Activity recognition computer vision algorithms can be used to detect the presence of autism-related behaviors, including what are termed "restricted and repetitive behaviors", or stimming, by diagnostic instruments. The limited data that …
View article: Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models
Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models Open
As the need for edge computing grows, many modern consumer devices now contain edge machine learning (ML) accelerators that can compute a wide range of neural network (NN) models while still fitting within tight resource constraints. We an…
View article: Activity Recognition with Moving Cameras and Few Training Examples:\n Applications for Detection of Autism-Related Headbanging
Activity Recognition with Moving Cameras and Few Training Examples:\n Applications for Detection of Autism-Related Headbanging Open
Activity recognition computer vision algorithms can be used to detect the\npresence of autism-related behaviors, including what are termed "restricted and\nrepetitive behaviors", or stimming, by diagnostic instruments. The limited data\nth…
View article: Improved Digital Therapy for Developmental Pediatrics Using Domain-Specific Artificial Intelligence: Machine Learning Study (Preprint)
Improved Digital Therapy for Developmental Pediatrics Using Domain-Specific Artificial Intelligence: Machine Learning Study (Preprint) Open
BACKGROUND Automated emotion classification could aid those who struggle to recognize emotions, including children with developmental behavioral conditions such as autism. However, most computer vision emotion recognition models are train…
View article: Guest Editorial: Robust Resource-Constrained Systems for Machine Learning
Guest Editorial: Robust Resource-Constrained Systems for Machine Learning Open
Machine learning (ML) is nowadays embedded in several computing devices, consumer electronics, and cyber-physical systems. Smart sensors are deployed everywhere, in applications such as wearables and perceptual computing devices, and intel…
View article: The Non-IID Data Quagmire of Decentralized Machine Learning
The Non-IID Data Quagmire of Decentralized Machine Learning Open
Many large-scale machine learning (ML) applications need to perform decentralized learning over datasets generated at different devices and locations. Such datasets pose a significant challenge to decentralized learning because their diffe…