Functionality Enhanced Memories for Edge-AI Embedded Systems

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The recollection of sensory information and subjective experience related to a personal past event depends on our episodic memory (EM). At the neural level, EM retrieval is linked with the reinstatement of hippocampal activity thought to recollect the sens ...

Accessing input data is a critical operation in data analytics: i) slow data access significantly degrades performance, and ii) storing everything in the fastest medium, i.e., memory, incurs high operational and hardware costs. Further, while GPUs offer in ...

Memory devices have returned to the spotlight due to increasing interest in using in-memory computing architectures to make data-driven algorithms more energy-efficient. One of the main advantages of this architecture is the efficient performance of vector ...

A painful episode can lead to a life-long increase in an individual's experience of pain. Fearful anticipation of imminent pain could play a role in this phenomenon, but the neurobiological underpinnings are unclear because fear can both suppress and enhan ...

Over the course of a lifetime, the human brain acquires an astonishing amount of semantic knowledge and autobiographical memories, often with an imprinting strong enough to allow detailed information to be recalled many years after the initial learning exp ...

Virtual Memory (VM) is a critical programming abstraction that is widely used in various modern computing platforms. With the rise of datacenter computing and birth of planet-scale online services, the semantic and capacity requirements from memory have ev ...

The Arctic is one of the most rapidly warming regions of the globe. Low-level clouds and fog modify the energy transfer from and to space and play a key role in the observed strong Arctic surface warming, a phenomenon commonly termed "Arctic amplification" ...

ML-based edge devices may face memory and computational errors that affect applications' reliability and performance. These errors can be the result of particular working conditions (e.g., radiation areas in physical experiments or avionics) or could be th ...

By supporting the access of multiple memory words at the same time, Bit-line Computing (BC) architectures allow the parallel execution of bit-wise operations in-memory. At the array periphery, arithmetic operations are then derived with little additional o ...

The demise of Moore's Law and Dennard scaling has resulted in diminishing performance gains for general-purpose processors, and so has prompted a surge in academic and commercial interest for hardware accelerators. Specialized hardware has already redefine ...

Multi-Scale computing systems aim at bringing the computing as close as possible to the data sources, to optimize both computation and networking. These systems are composed of at least three computing layers: the terminal layer, the edge layer, and the cl ...

Nuclear magnetic resonance (NMR) methods are powerful tools employed in many fields, including physics, chemistry, material science, biology, and medicine. The use of NMR methodologies in an even wider range of applications is often hindered by the relativ ...

Today, we are witnessing the Internet of Things (IoT) revolution, which facilitates and improves our lives in many aspects, but comes with several challenges related to the technology deployment at large scales. Handling ever growing amounts of information ...

GaN metal-oxide-semiconductor high electron mobility transistors (MOS)HEMTs) offer outstanding properties for next-generation power electronics devices. The high conductivity, high voltage blocking capability, high operation frequency, and device-level int ...

GeSn is a promising group-IV semiconductor material for on-chip Si photonics devices and high-mobility transistors. These devices require the use of doped GeSn regions, achieved preferably in situ during epitaxy. From the electronic valence point of view, ...

Functionality Enhanced Memories for Edge-AI Embedded Systems

Chat with Graph Search

Bodily self-consciousness as a framework to link sensory information and self-related components of episodic memory: behavioral, neuroimaging, and clinical evidence

HetCache: Synergising NVMe Storage and GPU acceleration for Memory-Efficient Analytics

How to Achieve Large-Area Ultra-Fast Operation of MoS 2 Monolayer Flash Memories?

Prefrontal engrams of long-term fear memory perpetuate pain perception

A theory of memory consolidation and synaptic pruning in cortical circuits

Rebooting Virtual Memory with Midgard

Aerosol and dynamical contributions to cloud droplet formation in Arctic low-level clouds

Hardware-Software co-design Methodologies for Edge AI Optimization

Bit-Line Computing for CNN Accelerators Co-Design in Edge AI Inference

Building Chips Faster: Hardware-Compiler Co-Design for Accelerated RTL Simulation

Special Session: Challenges and Opportunities for Sustainable Multi-Scale Computing Systems

Single Chip Dynamic Nuclear Polarization Microsystems

Energy Efficient Sensing using Steep Slope Devices

LiNiO Junction Gate for High-performance Enhancement-mode GaN Power Transistor

Surfactant behavior and limited incorporation of indium during in situ doping of GeSn grown by molecular beam epitaxy