Massoud Pedram

Bio: Massoud Pedram is an academic researcher from University of Southern California. The author has contributed to research in topics: Energy consumption & CMOS. The author has an hindex of 77, co-authored 780 publications receiving 23047 citations. Previous affiliations of Massoud Pedram include University of California, Berkeley & Syracuse University.

Energy Efficiency in 5G Cellular Network Systems

Abstract: Editor’s note: Fifth-generation (5G) cellular network will significantly enhance the amount of mobile data traffic. This article presents various resource allocation and power management problems in 5G cellular networks. It highlights multiple techniques that maximize the energy efficiency while meeting performance and QoS requirements. —Partha Pratim Pande, Washington State University

Deploying Customized Data Representation and Approximate Computing in Machine Learning Applications

Abstract: Major advancements in building general-purpose and customized hardware have been one of the key enablers of versatility and pervasiveness of machine learning models such as deep neural networks. To sustain this ubiquitous deployment of machine learning models and cope with their computational and storage complexity, several solutions such as low-precision representation of model parameters using fixed-point representation and deploying approximate arithmetic operations have been employed. Studying the potency of such solutions in different applications requires integrating them into existing machine learning frameworks for high-level simulations as well as implementing them in hardware to analyze their effects on power/energy dissipation, throughput, and chip area. Lop is a library for design space exploration that bridges the gap between machine learning and efficient hardware realization. It comprises a Python module, which can be integrated with some of the existing machine learning frameworks and implements various customizable data representations including fixed-point and floating-point as well as approximate arithmetic operations. Furthermore, it includes a highly-parameterized Scala module, which allows synthesizing hardware based on the said data representations and arithmetic operations. Lop allows researchers and designers to quickly compare quality of their models using various data representations and arithmetic operations in Python and contrast the hardware cost of viable representations by synthesizing them on their target platforms (e.g., FPGA or ASIC). To the best of our knowledge, Lop is the first library that allows both software simulation and hardware realization using customized data representations and approximate computing techniques.

A Statistical Static Timing Analysis Tool for Superconducting Single-Flux-Quantum Circuits

Abstract: As a beyond-CMOS technology, superconducting single-flux-quantum (SFQ) technology promises fast processing speed and excellent energy efficiency. With the increasing complexity of SFQ circuits, the accurate and fast estimation of the workable clock period under process variation becomes more urgent. However, the estimation of the minimum workable clock period is difficult due to the spatial correlation of physical parameters and the non-normal distribution of timing parameters (propagation delay, setup time, and hold time). Therefore, a good statistical timing analysis (SSTA) tool for SFQ circuits is necessary. This paper presents a bootstrap-based statistical static timing analysis tool called qSSTA. qSSTA can reasonably estimate a minimum workable clock period by executing a large amount of bootstrap iterations from the discrete sampling spaces of all gates under a certain correlation specification. By applying path pruning methods, qSSTA skips the calculations on unimportant paths and hence reduce run time and memory. Experimental results show that the size of important paths could be small. Among 19114 paths of the 16-bit integer divider, only 73 paths are important to estimate minimum workable clock period. We only need 84.21 seconds to run 10,000 iterations.

An electricity trade model for multiple power distribution networks in smart energy systems

Abstract: The future smart energy systems are projected to be decentralized power networks, each consisting of various types of renewable power generators that serve a small group of energy users. Interaction between different power networks through energy trading over a marketplace provides the chance to fully utilize the capacity of each power generator type. As a result of this interaction, the power generation and distribution levels can be decided for each time slot in order to achieve a maximal utility. In this paper, an electricity trade model is introduced for decentralized power networks to deal with the utility maximization problem. In the proposed model, multiple power networks can trade among each other and thus each of them can achieve a utility increase from making use of its comparative advantage on power generation during a certain period of time. The model is studied from several special scenarios to a more general scenario and an efficient solution is presented for each scenario. Experimental result validates the accuracy and efficiency of the presented solutions.

Calculation of ramp response of lossy transmission lines using two-port network functions

Abstract: In this paper, we present a new analytical approach for computing the ramp response of an RLC interconnect line with a pure capacitive load. The approach is based on the two-port representation of the transmission line and accounts for the output resistance of the driver and the line inductance. The results of our analysis are compared with the results of HSPICE simulations demonstrating the high accuracy of our solution under various values of driver, interconnect, and load impedances.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.