A High-Precision Implementation of the Sigmoid Activation Function for Computing-in-Memory Architecture

Computing-In-Memory (CIM), based on non-von Neumann architecture, has lately received significant attention due to its lower overhead in delay and higher energy efficiency in convolutional and fully-connected neural network computing. Growing works have given the priority to researching the array of memory and peripheral circuits to achieve multiply-and-accumulate (MAC) operation, but not enough attention has been paid to the high-precision hardware implementation of non-linear layers up to now, which still causes time overhead and power consumption. Sigmoid is a widely used non-linear activation function and most of its studies provided an approximation of the function expression rather than totally matched, inevitably leading to considerable error. To address this issue, we propose a high-precision circuit implementation of the sigmoid, matching the expression exactly for the first time. The simulation results with the SMIC 40 nm process suggest that the proposed circuit implemented high-precision sigmoid perfectly achieves the properties of the ideal sigmoid, showing the maximum error and average error between the proposed simulated sigmoid and ideal sigmoid is 2.74% and 0.21%, respectively. In addition, a multi-layer convolutional neural network based on CIM architecture employing the simulated high-precision sigmoid activation function verifies the similar recognition accuracy on the test database of handwritten digits compared to utilize the ideal sigmoid in software, with online training achieving 97.06% and with offline training achieving 97.74%.

Dynamic Processes in a Superconducting Adiabatic Neuron with Non-Shunted Josephson Contacts

We investigated the dynamic processes in a superconducting neuron based on Josephson contacts without resistive shunting (SC-neuron). Such a cell is a key element of perceptron-type neural networks that operate in both classical and quantum modes. The analysis of the obtained results allowed us to find the mode when the transfer characteristic of the element implements the “sigmoid” activation function. The numerical approach to the analysis of the equations of motion and the Monte Carlo method revealed the influence of inertia (capacitances), dissipation, and temperature on the dynamic characteristics of the neuron.

Coefficient Bounds for Al-Oboudi Type Bi-univalent Functions based on a Modified Sigmoid Activation Function and Horadam Polynomials

Using the Al-Oboudi type operator, we present and investigate two special families of bi-univalent functions in $\mathfrak{D}$, an open unit disc, based on $\phi(s)=\frac{2}{1+e^{-s} },\,s\geq0$, a modified sigmoid activation function (MSAF) and Horadam polynomials. We estimate the initial coefficients bounds for functions of the type $g_{\phi}(z)=z+\sum\limits_{j=2}^{\infty}\phi(s)d_jz^j$ in these families. Continuing the study on the initial cosfficients of these families, we obtain the functional of Fekete-Szeg\"o for each of the two families. Furthermore, we present few interesting observations of the results investigated.

Speeding up quantum perceptron via shortcuts to adiabaticity

The quantum perceptron is a fundamental building block for quantum machine learning. This is a multidisciplinary field that incorporates abilities of quantum computing, such as state superposition and entanglement, to classical machine learning schemes. Motivated by the techniques of shortcuts to adiabaticity, we propose a speed-up quantum perceptron where a control field on the perceptron is inversely engineered leading to a rapid nonlinear response with a sigmoid activation function. This results in faster overall perceptron performance compared to quasi-adiabatic protocols, as well as in enhanced robustness against imperfections in the controls.

FOREIGN TOURIST ARRIVAL FORECASTING TO BALI USING CASCADE FORWARD BACKPROPAGATION

Bali has a recognized tourism potential in the world arena. In order to improve the quality and development of the tourism sector in the midst of global competition, it is necessary to formulate appropriate strategies by decision makers such as private parties and government. In support of more accurate decision making, the authors make a system of forecasting the number of foreign tourist visits to Bali Province using Cascade Forward Backpropagation (CFB) method with coverage of Australia, Japan, and United Kingdom which are the top 3 countries with the highest foreign tourist arrival to Bali in that years. Factors used as input in forecasting include the number of visits of foreign tourists the previous year, the population of countries of origin of foreign tourists, Gross Domestic Product at current prices of countries of origin of foreign tourists, and Relative Consumer Price Index Origin of foreign tourists. In this study, optimization of activation function parameters, hidden neurons, and learning rate to obtain forecasting results with the lowest error rate. Forecasting results using the CFB method produces a fairly good accuracy with MAPE range of 6 - 30% where the activation function tanh work better than sigmoid activation function.

PERAMALAN KUNJUNGAN WISATAWAN MANCANEGARA KE PROVINSI BALI MENGGUNAKAN METODE ARTIFICIAL NEURAL NETWORK

Bali has an increasing tourism potential. This is evidenced by the increasing number of foreign tourist visits to Bali Province each year. Although Bali's tourism trends have continued to increase over the past few years, efforts to improve the quality of Bali tourism need to be made. One way is to do forecasting. To support improvement efforts in Bali's tourism sector, the author created a forecasting system for foreign tourists to Bali province using artificial neural network methods with back propagation algorithms. Artificial Neural Networks with back propagation algorithms are neural network algorithms by finding optimal weight values. The forecast results using the binary sigmoid activation function were obtained by 489,862 foreign tourists in November 2019 with MAPE at 1.62% and 487,342 foreign tourists in December 2019 with MAPE of 11.78%. The forecast results using the bipolar sigmoid activation function were obtained by 493,200 foreign tourists in November 2019 with MAPE of 0.95% and 484,090 foreign tourists in December 2019 with MAPE of 12.37%.