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

Token pruning has emerged as an effective solution to speed up the inference of large Transformer models. However, prior work on accelerating Vision Transformer (ViT) models requires training from scratch or fine-tuning with additional parameters, which prevents a simple plug-and-play. To avoid high training costs during the deployment stage, we present a fast training-free compression framework enabled by (i) a dense feature extractor in the initial layers; (ii) a sharpness-minimized model which is more compressible; and (iii) a local-global token merger that can exploit spatial relationships at various contexts. We applied our framework to various ViT and DeiT models and achieved up to 2x reduction in FLOPS and 1.8x speedup in inference throughput with<1% accuracy loss, while saving two orders of magnitude shorter training times than existing approaches. Code will be available at https://github.com/johnheo/fast-compress-vit

A Fast Training-Free Compression Framework for Vision Transformers

Superconducting Single Flux Quantum (SFQ) logic with switching delay of 1ps and switching energy of 10−19J is a potential emerging candidate for replacing Complementary Metal Oxide Semiconductor (CMOS) to achieve very high speed and ultra energy efficiency. Conventional SFQ circuits need Full Path Balancing (FPB), which tends to require insertion of many path balancing buffers (D-Flip-Flops). FPB method increases total power consumption as well as total area of the chip. This article presents a novel scheme for realization of superconducting SFQ circuits by introducing a new depth-bounded graph partitioning algorithm in combination with a dual clocking method (slow and fast clock pulses) that minimizes the aforesaid path balancing overheads. Experimental results show that the proposed solution reduces total number of path balancing buffers and total static power consumption by an average of 2.68× and 60%, respectively, when compared to the best of other methods for realizing SFQ circuits. However, our scheme degrades the peak throughput; therefore, it is especially valuable when the actual throughput of the SFQ circuit is much lower than the peak theoretical throughput. This is typically the case due to high-level data dependencies of the application that feeds data into an SFQ circuit.

Depth-bounded Graph Partitioning Algorithm and Dual Clocking Method for Realization of Superconducting SFQ Circuits

The usage of energy storage devices in data centers has been widely studied for the purpose of peak shaving in the context of dynamic utility pricing. To effectively achieve peak shaving in a data center with energy storage capability, a joint optimization framework is proposed to solve the task assignment problem and the energy storage management problem. The power hierarchy of a data center is modeled as a tree with battery arrays connected to each node, which is a generalization of common energy storage deployment topologies including the centralized structure and the rack/server-level distributed structure. A multi-dimensional resource request model is adopted based on released cluster traces in order to capture the complex dynamics of the workload of a data center. In addition, the rate capacity effect and aging effect are considered when modeling the batteries. A progressive refinement approach is used to solve the optimization problem. Experimental results show that the proposed algorithm consistently outperforms some baseline algorithms.

Efficient Peak Shaving in a Data Center by Joint Optimization of Task Assignment and Energy Storage Management

This paper addresses the problem of profit maximization for a data center with battery banks deployed at various levels of the power hierarchy. An optimization framework that covers the request dispatch, server resource allocation, and battery charging management is proposed. Instead of controlling the input/output power of the batteries after knowing the power profile of all other components of the data center as in a set of prior work, an optimal management policy is proposed which adjusts the power consumption (or supply) of servers and the battery banks at the same time. A response time dependent revenue model is adopted based on the delay estimation using the generalized processor sharing model. The rate capacity effect and the state of health degradation of the batteries, as well as the conversion and transmission loss in the power delivery network, are considered for the purpose of accurate power modeling and utility cost estimation. It is shown that the problem can be transformed into a series of convex optimization problems and then solved using standard solvers.

A Joint Optimization Framework for Request Scheduling and Energy Storage Management in a Data Center

Given the criticality of energy awareness in wireless networks, it has become essential to devise an improved definition of the network lifetime at the system design stage. The new definition must capture the life profile of the network while accounting for its functionality and specific design parameters. This paper presents the notion of network durability, which captures the spatiotemporal life/death patterns of devices in a wireless network by examining the time evolution of spatial patterns according to which devices are progressively forced to exit the network having exhausted their energy resource. Using network durability, we show how networks can satisfy different levels of monitoring criticality, even when they exhibit the same conventionally defined lifetime. Finally, as an example application, we consider a heterogeneous location-aware modulation scheme where the proposed durability model is effectively employed to characterize the network lifetime.

/pdf/durability-of-wireless-networks-of-battery-powered-devices-43i6z4oun2.pdf

Massoud Pedram

Papers

A Fast Training-Free Compression Framework for Vision Transformers

Depth-bounded Graph Partitioning Algorithm and Dual Clocking Method for Realization of Superconducting SFQ Circuits

Efficient Peak Shaving in a Data Center by Joint Optimization of Task Assignment and Energy Storage Management

A Joint Optimization Framework for Request Scheduling and Energy Storage Management in a Data Center

Durability of Wireless Networks of Battery-Powered Devices