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

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Gctf: Real-time CTF determination and correction

This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Coverage control for mobile sensing networks

/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

Deep learning (DL) techniques have obtained remarkable achievements on various tasks, such as image recognition, object detection, and language modeling. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering its wide application. Meanwhile, automated machine learning (AutoML) is a promising solution for building a DL system without human assistance and is being extensively studied. This paper presents a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. According to the DL pipeline, we introduce AutoML methods – covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS) – with a particular focus on NAS, as it is currently a hot sub-topic of AutoML. We summarize the representative NAS algorithms’ performance on the CIFAR-10 and ImageNet datasets and further discuss the following subjects of NAS methods: one/two-stage NAS, one-shot NAS, joint hyperparameter and architecture optimization, and resource-aware NAS. Finally, we discuss some open problems related to the existing AutoML methods for future research.

AutoML: A survey of the state-of-the-art

Synchronized stochastic gradient descent (SGD) optimizers with data parallelism are widely used in training large-scale deep neural networks. Although using larger mini-batch sizes can improve the system scalability by reducing the communication-to-computation ratio, it may hurt the generalization ability of the models. To this end, we build a highly scalable deep learning training system for dense GPU clusters with three main contributions: (1) We propose a mixed-precision training method that significantly improves the training throughput of a single GPU without losing accuracy. (2) We propose an optimization approach for extremely large mini-batch size (up to 64k) that can train CNN models on the ImageNet dataset without losing accuracy. (3) We propose highly optimized all-reduce algorithms that achieve up to 3x and 11x speedup on AlexNet and ResNet-50 respectively than NCCL-based training on a cluster with 1024 Tesla P40 GPUs. On training ResNet-50 with 90 epochs, the state-of-the-art GPU-based system with 1024 Tesla P100 GPUs spent 15 minutes and achieved 74.9\% top-1 test accuracy, and another KNL-based system with 2048 Intel KNLs spent 20 minutes and achieved 75.4\% accuracy. Our training system can achieve 75.8\% top-1 test accuracy in only 6.6 minutes using 2048 Tesla P40 GPUs. When training AlexNet with 95 epochs, our system can achieve 58.7\% top-1 test accuracy within 4 minutes, which also outperforms all other existing systems.

Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes.

To enhance environmental sustainability, many countries will electrify their transportation systems in their future smart city plans, so the number of electric vehicles (EVs) running in a city will grow significantly. There are many ways to recharge EVs' batteries and charging stations will be considered as the main source of energy. The locations of charging stations are critical; they should not only be pervasive enough such that an EV anywhere can easily access a charging station within its driving range, but also widely spread so that EVs can cruise around the whole city upon being recharged. Based on these new perspectives, we formulate the EV charging station placement problem (EVCSPP) in this paper. We prove that the problem is nondeterministic polynomial-time hard. We also propose four solution methods to tackle EVCSPP, and evaluate their performance on various artificial and practical cases. As verified by the simulation results, the methods have their own characteristics and they are suitable for different situations depending on the requirements for solution quality, algorithmic efficiency, problem size, nature of the algorithm, and existence of system prerequisite.

Electric Vehicle Charging Station Placement: Formulation, Complexity, and Solutions

To enhance environmental sustainability, many countries will electrify their transportation systems in their future smart city plans. So the number of electric vehicles (EVs) running in a city will grow significantly. There are many ways to re-charge EVs' batteries and charging stations will be considered as the main source of energy. The locations of charging stations are critical; they should not only be pervasive enough such that an EV anywhere can easily access a charging station within its driving range, but also widely spread so that EVs can cruise around the whole city upon being re-charged. Based on these new perspectives, we formulate the Electric Vehicle Charging Station Placement Problem (EVCSPP) in this paper. We prove that the problem is non-deterministic polynomial-time hard. We also propose four solution methods to tackle EVCSPP and evaluate their performance on various artificial and practical cases. As verified by the simulation results, the methods have their own characteristics and they are suitable for different situations depending on the requirements for solution quality, algorithmic efficiency, problem size, nature of the algorithm, and existence of system prerequisite.

SOAP3 is the first short read alignment tool that leverages the multi-processors in a graphic processing unit (GPU) to achieve a drastic improvement in speed. We adapted the compressed full-text index (BWT) used by SOAP2 in view of the advantages and disadvantages of GPU. When tested with millions of Illumina Hiseq 2000 length-100 bp reads, SOAP3 takes < 30 s to align a million read pairs onto the human reference genome and is at least 7.5 and 20 times faster than BWA and Bowtie, respectively. For aligning reads with up to four mismatches, SOAP3 aligns slightly more reads than BWA and Bowtie; this is because SOAP3, unlike BWA and Bowtie, is not heuristic-based and always reports all answers.

Xiaowen Chu

Papers

AutoML: A survey of the state-of-the-art

Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes.

Electric Vehicle Charging Station Placement: Formulation, Complexity, and Solutions

Electric Vehicle Charging Station Placement: Formulation, Complexity, and Solutions

SOAP3: ultra-fast GPU-based parallel alignment tool for short reads.