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

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

The PASCAL Visual Object Classes Challenge

The paper “Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification” by Joy Buolamwini and Timnit Gebru, that will be presented at the Conference on Fairness, Accountability, and Transparency (FAT*) in February 2018, evaluates three commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition. The study finds these services to have recognition capabilities that are not balanced over genders and skin tones [1]. In particular, the authors show that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men.

/pdf/gender-shades-intersectional-accuracy-disparities-in-4qgeu0c1i3.pdf

Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

A morphable model for the synthesis of 3D faces

http://romisatriawahono.net/lecture/rm/survey/computer%20vision/Gala%20-%20Person%20Reidentification%20-%202014.pdf

Editor's Choice Article: A survey of approaches and trends in person re-identification

Monocular 3D facial shape reconstruction from a single 2D facial image has been an active research area due to its wide applications. Inspired by the success of deep neural networks (DNN), we propose a DNN-based approach for End-to-End 3D FAce Reconstruction (UH-E2FAR) from a single 2D image. Different from recent works that reconstruct and refine the 3D face in an iterative manner using both an RGB image and an initial 3D facial shape rendering, our DNN model is end-to-end, and thus the complicated 3D rendering process can be avoided. Moreover, we integrate in the DNN architecture two components, namely a multi-task loss function and a fusion convolutional neural network (CNN) to improve facial expression reconstruction. With the multi-task loss function, 3D face reconstruction is divided into neutral 3D facial shape reconstruction and expressive 3D facial shape reconstruction. The neutral 3D facial shape is class-specific. Therefore, higher layer features are useful. In comparison, the expressive 3D facial shape favors lower or intermediate layer features. With the fusion-CNN, features from different intermediate layers are fused and transformed for predicting the 3D expressive facial shape. Through extensive experiments, we demonstrate the superiority of our end-to-end framework in improving the accuracy of 3D face reconstruction.

/pdf/end-to-end-3d-face-reconstruction-with-deep-neural-networks-3yu4vtgd3r.pdf

End-to-End 3D Face Reconstruction with Deep Neural Networks

http://analisedemarcha.com/papers/biomecanica/SYS/FishEyeCalibration-PR96.pdf

Intrinsic parameter calibration procedure for a (high-distortion) fish-eye lens camera with distortion model and accuracy estimation*☆

Osteosarcoma is a highly malignant bone neoplasm of children and young adults. It is characterized by extremely complex karyotypes and high frequency of chromosomal amplifications. Currently, only the histological response (degree of necrosis) to therapy represent gold standard for predicting the outcome in a patient with non-metastatic osteosarcoma at the time of definitive surgery. Patients with lower degree of necrosis have a higher risk of relapse and poor outcome even after chemotherapy and complete resection of the primary tumor. Therefore, a better understanding of the underlying molecular genetic events leading to tumor initiation and progression could result in the identification of potential diagnostic and therapeutic targets. We used a genome-wide screening method – array based comparative genomic hybridization (array-CGH) to identify DNA copy number changes in 48 patients with osteosarcoma. We applied fluorescence in situ hybridization (FISH) to validate some of amplified clones in this study. Clones showing gains (79%) were more frequent than losses (66%). High-level amplifications and homozygous deletions constitute 28.6% and 3.8% of tumor genome respectively. High-level amplifications were present in 238 clones, of which about 37% of them showed recurrent amplification. Most frequently amplified clones were mapped to 1p36.32 (PRDM16), 6p21.1 (CDC5L, HSPCB, NFKBIE), 8q24, 12q14.3 (IFNG), 16p13 (MGRN1), and 17p11.2 (PMP22 MYCD, SOX1,ELAC27). We validated some of the amplified clones by FISH from 6p12-p21, 8q23-q24, and 17p11.2 amplicons. Homozygous deletions were noted for 32 clones and only 7 clones showed in more than one case. These 7 clones were mapped to 1q25.1 (4 cases), 3p14.1 (4 cases), 13q12.2 (2 cases), 4p15.1 (2 cases), 6q12 (2 cases), 6q12 (2 cases) and 6q16.3 (2 cases). This study clearly demonstrates the utility of array CGH in defining high-resolution DNA copy number changes and refining amplifications. The resolution of array CGH technology combined with human genome database suggested the possible target genes present in the gained or lost clones.

/pdf/genome-wide-array-comparative-genomic-hybridization-analysis-28z4ukjgo4.pdf

Shishir K. Shah

Papers

Editor's Choice Article: A survey of approaches and trends in person re-identification

End-to-End 3D Face Reconstruction with Deep Neural Networks

Intrinsic parameter calibration procedure for a (high-distortion) fish-eye lens camera with distortion model and accuracy estimation*☆

Genome-wide array comparative genomic hybridization analysis reveals distinct amplifications in osteosarcoma.

End-to-end 3D face reconstruction with deep neural networks