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

物件導向軟體之架構(Object-Oriented Software Construction)探討

A prevalent and pervasive view of designing is that it can be modeled using variables and decisions made about what values should be taken by these variables. The activity of designing is carried out with the expectation that the designed artifact will operate in the natural world and the social world. These worlds impose constraints on the variables and their values; so, design could be described as a goal-oriented, constrained, decision- making activity. However, design distinguish- es itself from other similarly described activities not only by its domain but also by additional necessary features. Designing involves exploration, exploring what variables might be appropriate. The process of explo- ration involves both goal variables and deci- sion variables. In addition, designing involves learning: Part of the exploration activity is learning about emerging features as a design proceeds. Finally, design activity occurs within two contexts: the context within which the designer operates and the context produced by the developing design itself. The designer’s perception of what the context is affects the implication of the context on the design. The context shifts as the designer’s perceptions change. Design activity can be now characterized as a goal-oriented, con- strained, decision-making, exploration, and learning activity that operates within a con- text that depends on the designer’s percep- tion of the context.

Design Prototypes: A Knowledge Representation Schema for Design

3D printing, more formally known as Additive Manufacturing (AM), is already being adopted for rapid prototyping and soon rapid manufacturing. This review provides a brief discussion about AM and also the most employed AM technologies for polymers. The commonly-used ASTM and ISO mechanical test standards which have been used by various research groups to test the strength of the 3D-printed parts have been reported. Also, a summary of an exhaustive amount of literature regarding the mechanical properties of 3D-printed parts is included, specifically, properties under different loading types such as tensile, bending, compressive, fatigue, impact and others. Properties at low temperatures have also been discussed. Further, the effects of fillers as well as post-processing on the mechanical properties have also been discussed. Lastly, several important questions to consider in the standardization of mechanical test methods have been raised.

Mechanical characterization of 3D-printed polymers

Materials for additive manufacturing

In most macroscale robotic systems, propulsion and controls are enabled through a physical tether or complex onboard electronics and batteries. A tether simplifies the design process but limits the range of motion of the robot, while onboard controls and power supplies are heavy and complicate the design process. Here, we present a simple design principle for an untethered, soft swimming robot with preprogrammed, directional propulsion without a battery or onboard electronics. Locomotion is achieved by using actuators that harness the large displacements of bistable elements triggered by surrounding temperature changes. Powered by shape memory polymer (SMP) muscles, the bistable elements in turn actuate the robot’s fins. Our robots are fabricated using a commercially available 3D printer in a single print. As a proof of concept, we show the ability to program a vessel, which can autonomously deliver a cargo and navigate back to the deployment point.

https://www.pnas.org/content/pnas/115/22/5698.full.pdf

Harnessing bistability for directional propulsion of soft, untethered robots.

Towards integrated performance-driven generative design tools

One of the hallmarks of engineering design is the design synthesis phase where the creativity of the designer most prominently comes into play as solutions are generated to meet underlying needs. Over the past decades, methodologies for generating concepts and design solutions have matured to the point that computation-based synthesis provides a means to explore a wider variety of solutions and take over more tedious design tasks. This paper reviews advances in function-based, grammar-based, and analogy-based synthesis approaches and their contributions to computational design synthesis research in the last decade.

/pdf/computer-based-design-synthesis-research-an-overview-50909as66b.pdf

Computer-Based Design Synthesis Research: An Overview

Performance-driven generative design methods are capable of producing concepts and stimulating solutions based on robust and rigorous models of design conditions and performance criteria. Using generative methods, the computer becomes a design generator in addition to its more conventional role as draftsperson, visualizor, data checker and performance analyst. To enable designers to readily develop meaningful input models, this paper describes a preliminary integration of a generative structural design system, eifForm, and an associative modeling system, Generative Components, through the use of XML models. An example is given involving generation of 20 lightweight, cantilever roof trusses for a saddle shaped stadium roof modeled in Generative Components. Synergies between the two systems and future extensions are discussed.

Natural composites exhibit exceptional mechanical performance that often arises from complex fiber arrangements within continuous matrices. Inspired by these natural systems, we developed a rotational 3D printing method that enables spatially controlled orientation of short fibers in polymer matrices solely by varying the nozzle rotation speed relative to the printing speed. Using this method, we fabricated carbon fiber–epoxy composites composed of volume elements (voxels) with programmably defined fiber arrangements, including adjacent regions with orthogonally and helically oriented fibers that lead to nonuniform strain and failure as well as those with purely helical fiber orientations akin to natural composites that exhibit enhanced damage tolerance. Our approach broadens the design, microstructural complexity, and performance space for fiber-reinforced composites through site-specific optimization of their fiber orientation, strain, failure, and damage tolerance.

https://www.pnas.org/content/pnas/115/6/1198.full.pdf

Kristina Shea

Papers

Harnessing bistability for directional propulsion of soft, untethered robots.

Towards integrated performance-driven generative design tools

Computer-Based Design Synthesis Research: An Overview

Towards integrated performance-driven generative design tools

Rotational 3D printing of damage-tolerant composites with programmable mechanics.