Searched for: subject%3A%22low%255C-power%22
(1 - 4 of 4)
document
Jiang, Longxing (author), Aledo Ortega, D. (author), van Leuken, T.G.R.M. (author)
Logarithmic quantization for Convolutional Neural Networks (CNN): a) fits well typical weights and activation distributions, and b) allows the replacement of the multiplication operation by a shift operation that can be implemented with fewer hardware resources. We propose a new quantization method named Jumping Log Quantization (JLQ). The key...
conference paper 2023
document
Jiang, Longxing (author)
Convolutional Neural Networks (CNN) have become a popular solution for computer vision problems. However, due to the high data volumes and intensive computation involved in CNNs, deploying CNNs on low-power hardware systems is still challenging.<br/>The power consumption of CNNs can be prohibitive in the most common implementation platforms:...
master thesis 2022
document
Hussaini, Said (author), Jiang, H. (author), Walsh, Paul (author), MacSweeney, Dermot (author), Makinwa, K.A.A. (author)
This paper presents a readout IC that uses an asynchronous capacitance-to-digital-converter (CDC) to digitize the capacitance of a touch sensor. A power-efficient tracking algorithm ensures that the CDC consumes negligible power consumption in the absence of touch events. To facilitate its use in wake-on-touch applications, the CDC can be...
journal article 2019
document
Hussaini, Said (author), Jiang, H. (author), Walsh, Paul (author), MacSweeney, Dermot (author), Makinwa, K.A.A. (author)
This paper presents a readout IC that uses an asynchronous charge-redistribution-based capacitance-to-digital-converter (CDC) to digitize the capacitance of a touch sensor. Thanks to the power efficient tracking algorithm, the CDC consumes negligible power consumption in the absence of touch events. To facilitate stand-alone or wake-on-touch...
conference paper 2018
Searched for: subject%3A%22low%255C-power%22
(1 - 4 of 4)