Michael S. Bernstein

Bio: Michael S. Bernstein is an academic researcher from Stanford University. The author has contributed to research in topics: Crowdsourcing & Computer science. The author has an hindex of 52, co-authored 191 publications receiving 42744 citations. Previous affiliations of Michael S. Bernstein include Association for Computing Machinery & Massachusetts Institute of Technology.

Embracing Error to Enable Rapid Crowdsourcing

Abstract: Microtask crowdsourcing has enabled dataset advances in social science and machine learning, but existing crowdsourcing schemes are too expensive to scale up with the expanding volume of data. To scale and widen the applicability of crowdsourcing, we present a technique that produces extremely rapid judgments for binary and categorical labels. Rather than punishing all errors, which causes workers to proceed slowly and deliberately, our technique speeds up workers' judgments to the point where errors are acceptable and even expected. We demonstrate that it is possible to rectify these errors by randomizing task order and modeling response latency. We evaluate our technique on a breadth of common labeling tasks such as image verification, word similarity, sentiment analysis and topic classification. Where prior work typically achieves a 0.25x to 1x speedup over fixed majority vote, our approach often achieves an order of magnitude (10x) speedup.

Apparition: Crowdsourced User Interfaces that Come to Life as You Sketch Them

Abstract: Prototyping allows designers to quickly iterate and gather feedback, but the time it takes to create even a Wizard-of-Oz prototype reduces the utility of the process. In this paper, we introduce crowdsourcing techniques and tools for prototyping interactive systems in the time it takes to describe the idea. Our Apparition system uses paid microtask crowds to make even hard-to-automate functions work immediately, allowing more fluid prototyping of interfaces that contain interactive elements and complex behaviors. As users sketch their interface and describe it aloud in natural language, crowd workers and sketch recognition algorithms translate the input into user interface elements, add animations, and provide Wizard-of-Oz functionality. We discuss how design teams can use our approach to reflect on prototypes or begin user studies within seconds, and how, over time, Apparition prototypes can become fully-implemented versions of the systems they simulate. Powering Apparition is the first self-coordinated, real-time crowdsourcing infrastructure. We anchor this infrastructure on a new, lightweight write-locking mechanism that workers can use to signal their intentions to each other.

Analytic Methods for Optimizing Realtime Crowdsourcing

Abstract: Realtime crowdsourcing research has demonstrated that it is possible to recruit paid crowds within seconds by managing a small, fast-reacting worker pool. Realtime crowds enable crowd-powered systems that respond at interactive speeds: for example, cameras, robots and instant opinion polls. So far, these techniques have mainly been proof-of-concept prototypes: research has not yet attempted to understand how they might work at large scale or optimize their cost/performance trade-offs. In this paper, we use queueing theory to analyze the retainer model for realtime crowdsourcing, in particular its expected wait time and cost to requesters. We provide an algorithm that allows requesters to minimize their cost subject to performance requirements. We then propose and analyze three techniques to improve performance: push notifications, shared retainer pools, and precruitment, which involves recalling retainer workers before a task actually arrives. An experimental validation finds that precruited workers begin a task 500 milliseconds after it is posted, delivering results below the one-second cognitive threshold for an end-user to stay in flow.

Examining Crowd Work and Gig Work Through The Historical Lens of Piecework

Abstract: The internet is empowering the rise of crowd work, gig work, and other forms of on-demand labor. A large and growing body of scholarship has attempted to predict the socio-technical outcomes of this shift, especially addressing three questions: 1) What are the complexity limits of on-demand work?, 2) How far can work be decomposed into smaller microtasks?, and 3) What will work and the place of work look like for workers? In this paper, we look to the historical scholarship on piecework — a similar trend of work decomposition, distribution, and payment that was popular at the turn of the 20th century — to understand how these questions might play out with modern on-demand work. We identify the mechanisms that enabled and limited piecework historically, and identify whether on-demand work faces the same pitfalls or might differentiate itself. This approach introduces theoretical grounding that can help address some of the most persistent questions in crowd work, and suggests design interventions that learn from history rather than repeat it.

Enhancing directed content sharing on the web

Abstract: To find interesting, personally relevant web content, people rely on friends and colleagues to pass links along as they encounter them. In this paper, we study and augment link-sharing via e-mail, the most popular means of sharing web content today. Armed with survey data indicating that active sharers of novel web content are often those that actively seek it out, we developed FeedMe, a plug-in for Google Reader that makes directed sharing of content a more salient part of the user experience. FeedMe recommends friends who may be interested in seeing content that the user is viewing, provides information on what the recipient has seen and how many emails they have received recently, and gives recipients the opportunity to provide lightweight feedback when they appreciate shared content. FeedMe introduces a novel design space within mixed-initiative social recommenders: friends who know the user voluntarily vet the material on the user's behalf. We performed a two-week field experiment (N=60) and found that FeedMe made it easier and more enjoyable to share content that recipients appreciated and would not have found otherwise.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.