The Architectural Implications of Multi-modal Detection Models for Autonomous Driving Systems
Object detection plays a pivotal in autonomous driving by enabling the vehicles to perceive
and comprehend their environment, thereby making informed decisions for safe navigation …
and comprehend their environment, thereby making informed decisions for safe navigation …
RT-MDM: Real-Time Scheduling Framework for Multi-DNN on MCU Using External Memory
S Kang, S Lee, H Koo, HS Chwa, J Lee - … of the 61st ACM/IEEE Design …, 2024 - dl.acm.org
As the application scope of DNNs executed on microcontroller units (MCUs) extends to time-
critical systems, it becomes important to ensure timing guarantees for increasing demand of …
critical systems, it becomes important to ensure timing guarantees for increasing demand of …
Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
W Tao, S He, K Lu, X Qu, G Li, J Wan… - … , Automation & Test …, 2024 - ieeexplore.ieee.org
Deploying neural networks on microcontroller units (MCUs) presents substantial challenges
due to their constrained computation and memory resources. Previous researches have …
due to their constrained computation and memory resources. Previous researches have …
XNOROP: a New Metric for Binary Neural Networks Performance Measurement
A Shakkouf, GV Sergeevich - 2024 36th Conference of Open …, 2024 - ieeexplore.ieee.org
The quantity of multiply–accumulate operations in a model (MACs) is a widely used metric in
the field of neural networks and deep learning. This metric expresses the computational cost …
the field of neural networks and deep learning. This metric expresses the computational cost …
Comparison of the Efficiency of a Neural Network for Image Recognition on Microcontrollers
RD Sharuiev, PV Popovych - 2024 - ela.kpi.ua
Анотація The paper is devoted to comparing two popular models of 32-bit microcontrollers
for working with neural networks for object recognition. The target devices were the ESP32 …
for working with neural networks for object recognition. The target devices were the ESP32 …
Comparison of the Efficiency of a Neural Network for Image Recognition on Microcontrollers
РД Шаруєв, ПВ Попович - Мікросистеми, Електроніка та Акустика, 2024 - elc.kpi.ua
The paper is devoted to comparing two popular models of 32-bit microcontrollers for working
with neural networks for object recognition. The target devices were the ESP32 and STM32 …
with neural networks for object recognition. The target devices were the ESP32 and STM32 …