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

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

https://web.cs.wpi.edu/~rail/files/ArgallEtAlRAS09.pdf

A survey of robot learning from demonstration

Humanoid robots working alongside humans in everyday environments is a long standing goal of the robotics community. To achieve this goal, methods for developing new robot behaviors that are intuitive and accessible to non-programmers are required. In this paper, we present a demonstration-based method for teaching distributed autonomous robots to coordinate their actions and perform collaborative multi-robot tasks. Within the presented framework, each robot learns an individual policy from teacher demonstrations using a confidence-based algorithm. Based on this learning approach, we contribute three techniques for teaching multi-robot coordination using different information sharing strategies. We evaluate and compare these approaches by teaching two Sony QRIO humanoid robots to perform three collaborative ball sorting tasks.

/pdf/teaching-collaborative-multi-robot-tasks-through-59zrartnrx.pdf

Teaching collaborative multi-robot tasks through demonstration

The development of hand-crafted action and dialog generation models for a social robot is a time consuming process that yields a solution only for the relatively narrow range of interactions envisioned by the programmers. In this paper, we propose a data-driven solution for interactive behavior generation that leverages online games as a means of collecting large-scale data corpora for human-robot interaction research. We present a system in which action and dialog models for a collaborative human-robot task are learned based on a reproduction of the task in a two-player online game called Mars Escape.

/pdf/crowdsourcing-hri-through-online-multiplayer-games-1tckn6970g.pdf

Crowdsourcing HRI through Online Multiplayer Games

CMRoboBits is a course offered at Carnegie Mellon University that introduces students to all the concepts needed to create a complete intelligent robot. In particular, the course focuses on the areas of perception, cognition, and action by using the Sony AIBO robot as the focus for the programming assignments. This course shows how an AIBO and its software resources make it possible for students to investigate and work with an unusually broad variety of AI topics within a single semester. While material presented in this article describes using AIBOs as the primary platform, the concepts presented in the course are not unique to the AIBO and can be applied on different kinds of robotic hardware.

/pdf/cmrobobits-creating-an-intelligent-aibo-robot-8wvmno7d49.pdf

CMRoboBits: Creating an Intelligent AIBO Robot

This paper presents our progress toward a user-guided manipulation framework for high degree-of-freedom robots operating in environments with limited communication. The system we propose consists of three components: (1) a user-guided perception interface that assists the user in providing task-level commands to the robot, (2) planning algorithms that autonomously generate robot motion while obeying relevant constraints, and (3) a trajectory execution and monitoring system which detects errors in execution. We report quantitative experiments performed on these three components and qualitative experiments of the entire pipeline with the PR2 robot turning a valve for the DARPA robotics challenge. We also describe how the framework was ported to the Hubo2+ robot with minimal changes which demonstrates its applicability to different types of robots.

/pdf/toward-a-user-guided-manipulation-framework-for-high-dof-5gdwdb3jie.pdf

Toward a user-guided manipulation framework for high-DOF robots with limited communication

Does progress in simulation translate to progress on robots? If one method outperforms another in simulation, how likely is that trend to hold in reality on a robot? We examine this question for embodied PointGoal navigation - developing engineering tools and a research paradigm for evaluating a simulator by its sim2real predictivity. First, we develop Habitat-PyRobot Bridge (HaPy), a library for seamless execution of identical code on simulated agents and robots - transferring simulation-trained agents to a LoCoBot platform with a one-line code change. Second, we investigate the sim2real predictivity of Habitat-Sim M. Savva et al., for PointGoal navigation. We 3D-scan a physical lab space to create a virtualized replica, and run parallel tests of 9 different models in reality and simulation. We present a new metric called Sim-vs-Real Correlation Coefficient (SRCC) to quantify predictivity. We find that SRCC for Habitat as used for the CVPR19 challenge is low (0.18 for the success metric), suggesting that performance differences in this simulator-based challenge do not persist after physical deployment. This gap is largely due to AI agents learning to exploit simulator imperfections - abusing collision dynamics to `slide' along walls, leading to shortcuts through otherwise non-navigable space. Naturally, such exploits do not work in the real world. Our experiments show that it is possible to tune simulation parameters to improve sim2real predictivity (e.g. improving SRCC
 Succ
 from 0.18 to 0.844) - increasing confidence that in-simulation comparisons will translate to deployed systems in reality.

Sonia Chernova

Papers

Teaching collaborative multi-robot tasks through demonstration

Crowdsourcing HRI through Online Multiplayer Games

CMRoboBits: Creating an Intelligent AIBO Robot

Toward a user-guided manipulation framework for high-DOF robots with limited communication

Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?