Dual Tree Single Clock (DTSC) Adiabatic Capacitive Neuron (ACN) circuits offer the potential for highly energy-efficient Artificial Neural Network (ANN) computation in full custom analog IC designs. The efficient mapping of Artificial Neuron (AN) abstract weights, extracted from the software-trained ANNs, onto physical ACN capacitance values has, however, yet to be fully researched. In this paper, we explore the unexpected hidden complexities, challenges and properties of the mapping, as well as, the ramifications for IC designers in terms accuracy, design and implementation. We propose an optimal, AN to ACN methodology, that promotes smaller chip sizes and improved overall classification accuracy, necessary for successful practical deployment. Using TensorFlow and Larq software frameworks, we train three different ANN networks and map their weights into the energy-efficient DTSC ACN capacitance value domain to demonstrate 100% functional equivalency. Finally, we delve into the impact of weight quantization on ACN performance using novel metrics related to practical IC considerations, such as IC floor space and comparator decision-making efficacy.

Moore Law states that transistor density will double every two years, which is sustained until today due to continuous multi-directional innovations, such as extreme ultraviolet lithography, novel patterning techniques etc., leading the semiconductor industry towards 3nm node and beyond. For any patterning scheme, the most important metric to evaluate the quality of printed patterns is EPE, with overlay being its largest contribution. Overlay errors can lead to fatal failures of IC devices such as short circuits or broken connections in terms of P2P electrical contacts. Therefore, it is essential to develop effective overlay analysis and control techniques to ensure good functionality of fabricated semiconductor devices. In this work we have used an imec N14 BEOL process flow using LELE patterning technique to print metal layers with minimum pitch of 48nm with 193i lithography. FF structures are decomposed into two mask layers (M1A and M1B) and then the LELE flow is carried out to make the final patterns. Since a single M1 layer is decomposed into two masks, control of overlay between the two masks is critical. The goal of this work is of two-fold as, (a) to quantify the impact of overlay on capacitance and (b) to see if we can predict the final capacitance measurements with selected machine learning models at an early stage. To do so, scatterometry spectra are collected on these electrical test structures at (a)post litho, (b)post TiN hardmask etch, and (c)post Cu plating and CMP. Critical Dimension and overlay measurements for line-space pattern are done with SEM post litho, post etch and post Cu CMP. Various machine learning models are applied to do the capacitance prediction with multiple metrology inputs at different steps of wafer processing. Finally, we demonstrate that by using appropriate machine learning models we are able to do better prediction of electrical results.

In this paper, we present a new approach for robust reading of identification and sensor data from chipless RFID sensor tags. For the first time, Machine Learning (ML) and Deep Learning (DL) regression modelling techniques are applied to a dataset of measured Radar Cross Section (RCS) data that has been derived from large-scale robotic measurements of custom-designed, 3-bit chipless RFID sensor tags. The robotic system is implemented using the first-of-its-kind automated data acquisition method using an ur16e industry-standard robot. A large data set of 9,600 Electromagnetic (EM) RCS signatures collected using the automated system is used to train and validate four ML models and four 1-dimensional Convolutional Neural Network (1D CNN) architectures. For the first time, we report an end-to-end design and implementation methodology for robust detection of identification (ID) and sensing data using ML/DL models. Also, we report, for the first time, the effect of varying tag surface shapes, tilt angles, and read ranges that were incorporated into the training of models for robust detection of ID and sensing values. The results show that all the models were able to generalise well on the given data. However, the 1D CNN models outperformed the conventional ML models in the detection of ID and sensing values. The best 1D CNN model architectures performed well with a low Root Mean Square Error (RSME) of 0.061 (0.87%) for tag ID and 0.0241 (3.44%) error for the capacitive sensing.

In this paper the concept of a machine learning based hands-on detection algorithm is proposed. The hand detection is implemented on the hardware side using a capacitive method. A sensor mat in the steering wheel detects a change in capacity as soon as the driver's hands come closer. The evaluation and final decision about hands-on or hands-off situations is done using machine learning. In order to find a suitable machine learning model, different models are implemented and evaluated. Based on accuracy, memory consumption and computational effort the most promising one is selected and ported on a micro controller. The entire system is then evaluated in terms of reliability and response time.