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 …

I and i

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

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.).

Machine learning

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.

Pattern Recognition and Machine Learning

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

After analyzing the limitations of the traditional description of CMOS circuits at the gate level, this paper introduces the notions of switching and signal variables for describing the switching states of MOS transistors and signals in CMOS circuits, respectively. Two connection operations for describing the interaction between MOS transistors and signals and a new description for CMOS circuits at the switch level are presented. This new description can be used to express the functional relationship between inputs and the output at the switch level. It can also be used to describe the circuit structure composed of various transistor switches. Based on the new description, the design of CMOS circuits at the switch level can be efficiently realized. It is expected that this will provide a basis for techniques for analyzing and optimizing the delay and power dissipation of CMOS circuits.

/pdf/a-new-description-of-cmos-circuits-at-switch-level-2pa3c7jqhz.pdf

A new description of CMOS circuits at switch-level

In this paper, we propose an efficient predefined structured sparsity-based ex-situ training framework for a hybrid CMOS-memristive neuromorphic hardware for deep neural network to significantly lower the power consumption and computational complexity and improve scalability. The structure is verified on a wide range of datasets including MNIST handwritten recognition, breast cancer prediction, and mobile health monitoring. The results of this study show that compared to its fully connected version, the proposed structure provides significant power reduction while maintaining high classification accuracy.

SpRRAM: A Predefined Sparsity Based Memristive Neuromorphic Circuit for Low Power Application

Recent efforts for improving the performance of neural network (NN) accelerators that meet today’s application requirements have given rise to a new trend of logic-based NN inference relying on fixed function combinational logic. Mapping such large Boolean functions with many input variables and product terms to digital signal processors (DSPs) on Field-programmable gate arrays (FPGAs) needs a novel framework considering the structure and reconfigurability of DSP blocks during this process. The proposed methodology in this article maps the fixed function combinational logic blocks to a set of Boolean functions where Boolean operations corresponding to each function are mapped to DSP devices rather than look-up tables on the FPGAs to take advantage of the high performance, low latency, and parallelism of DSP blocks. This article also presents an innovative design and optimization methodology for compilation and mapping of NNs, utilizing fixed function combinational logic to DSPs on FPGAs employing high-level synthesis flow. Our experimental evaluations across several datasets and selected NNs demonstrate the comparable performance of our framework in terms of the inference latency and output accuracy compared to prior art FPGA-based NN accelerators employing DSPs.

https://dl.acm.org/doi/pdf/10.1145/3559543

Efficient Compilation and Mapping of Fixed Function Combinational Logic onto Digital Signal Processors Targeting Neural Network Inference and Utilizing High-level Synthesis

A number of researches have addressed the problem of minimizing power dissipation during module allocation and binding [RJ94] [KC97], scheduling and allocation [MC95], register allocation and binding [RJ94] [CP95a] and trading area for lower power through pipelining or parallelization combined with voltage scaling [GOC94] [CPRR92], scheduling using multiple supply voltages [CP96a, CP97] [RS95] [JR96].

Power-Optimal Module Allocation and Binding

Although CMOS technology scaling has proceeded to sub-20nm nodes, FinFET devices are considered as the technology-of-choice for sub-20nm technology nodes due to the improved gate control [1]. On the other hand, voltage scaling provides us an energy efficient solution to the VLSI design, such as the near-threshold computing technique [2]. This work investigates the performance and energy consumption of LEON3 processor under technology and voltage scaling. Specifically, in order to study the impact of technology and voltage scaling, this work (i) develops 7nm gate length FinFET, ITRS 7nm FinFET (with 11nm actual gate length), ITRS 16nm CMOS, and ITRS 22nm CMOS Verilog-A device models using Synopsys TCAD tools [3], (ii) builds up the standard cell libraries using the developed Verilog-A models for the four previously mentioned technology nodes under a set of different supply voltage levels (i.e., from near-threshold to super-threshold), and (iii) synthesizes LEON3 processor (datapath plus L1 and L2 caches) using the developed standard cell libraries to compare the impact of technology and voltage scaling on the performance and energy consumption of LEON3 processor.

/pdf/impact-of-technology-and-voltage-scaling-on-leon3-processor-2vxc4umnt5.pdf

Massoud Pedram

Papers

A new description of CMOS circuits at switch-level

SpRRAM: A Predefined Sparsity Based Memristive Neuromorphic Circuit for Low Power Application

Efficient Compilation and Mapping of Fixed Function Combinational Logic onto Digital Signal Processors Targeting Neural Network Inference and Utilizing High-level Synthesis

Power-Optimal Module Allocation and Binding

Impact of technology and voltage scaling on LEON3 processor performance and energy