Approximate computing: Concepts, architectures, challenges, applications, and future directions
AM Dalloo, AJ Humaidi, AK Al Mhdawi… - IEEE …, 2024 - ieeexplore.ieee.org
The unprecedented progress in computational technologies led to a substantial proliferation
of artificial intelligence applications, notably in the era of big data and IoT devices. In the …
of artificial intelligence applications, notably in the era of big data and IoT devices. In the …
Potential of edge machine learning for instrumentation
New developments in radiation and photonic detectors improve resolution, sensitivity, size,
and rate, all of which contribute to a gigantic increase in the data production rate. Moving …
and rate, all of which contribute to a gigantic increase in the data production rate. Moving …
A hybrid radix-4 and approximate logarithmic multiplier for energy efficient image processing
Multiplication is an essential image processing operation commonly implemented in
hardware DSP cores. To improve DSP cores' area, speed, or energy efficiency, we can …
hardware DSP cores. To improve DSP cores' area, speed, or energy efficiency, we can …
An efficient selection-based KNN architecture for smart embedded hardware accelerators
K-Nearest Neighbor (kNN) is an efficient algorithm used in many applications, eg, text
categorization, data mining, and predictive analysis. Despite having a high computational …
categorization, data mining, and predictive analysis. Despite having a high computational …
Trade-off between accuracy and computational cost with neural architecture search: A novel strategy for tactile sensing design
This letter presents a neural architecture search to optimize tactile elaboration systems
taking into account the computational cost of the whole pipeline consisting of data …
taking into account the computational cost of the whole pipeline consisting of data …
1-D convolutional neural networks for touch modalities classification
Artificial tactile systems can facilitate the life of people suffering from a loss of the sense of
touch. These systems use sensors and digital, battery-operated embedded units for data …
touch. These systems use sensors and digital, battery-operated embedded units for data …
[HTML][HTML] Optimizing Machine Learning Models with Data-level Approximate Computing: The Role of Diverse Sampling, Precision Scaling, Quantization and Feature …
AM Dalloo, AJ Humaidi - Results in Engineering, 2024 - Elsevier
Efficiency, low-power consumption, and real-time processing in embedded machine
learning implementations are critical, particularly for models deployed in environments with …
learning implementations are critical, particularly for models deployed in environments with …
[HTML][HTML] FPGA-based ML adaptive accelerator: A partial reconfiguration approach for optimized ML accelerator utilization
The relentless increase in data volume and complexity necessitates advancements in
machine learning methodologies that are more adaptable. In response to this challenge, we …
machine learning methodologies that are more adaptable. In response to this challenge, we …
An approximate GEMM unit for energy-efficient object detection
Edge computing brings artificial intelligence algorithms and graphics processing units closer
to data sources, making autonomy and energy-efficient processing vital for their design …
to data sources, making autonomy and energy-efficient processing vital for their design …
Hardware Implementation of Calibration Data Loading in Device Driver for an SPI Peripheral
H Shinozaki, A Yamawaki - Proceedings of the 2024 6th International …, 2024 - dl.acm.org
As the IoT progresses, various SoCs are being developed. If a SoC is in high demand, the
development cost per chip is small, but if the demand is localized, the development cost is …
development cost per chip is small, but if the demand is localized, the development cost is …