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.

Information Maximizing Visual Question Generation

Abstract: Though image-to-sequence generation models have become overwhelmingly popular in human-computer communications, they suffer from strongly favoring safe generic questions ("What is in this picture?"). Generating uninformative but relevant questions is not sufficient or useful. We argue that a good question is one that has a tightly focused purpose --- one that is aimed at expecting a specific type of response. We build a model that maximizes mutual information between the image, the expected answer and the generated question. To overcome the non-differentiability of discrete natural language tokens, we introduce a variational continuous latent space onto which the expected answers project. We regularize this latent space with a second latent space that ensures clustering of similar answers. Even when we don't know the expected answer, this second latent space can generate goal-driven questions specifically aimed at extracting objects ("what is the person throwing"), attributes, ("What kind of shirt is the person wearing?"), color ("what color is the frisbee?"), material ("What material is the frisbee?"), etc. We quantitatively show that our model is able to retain information about an expected answer category, resulting in more diverse, goal-driven questions. We launch our model on a set of real world images and extract previously unseen visual concepts.

Pay It Backward: Per-Task Payments on Crowdsourcing Platforms Reduce Productivity

Abstract: Paid crowdsourcing marketplaces have gained popularity by using piecework, or payment for each microtask, to incentivize workers. This norm has remained relatively unchallenged. In this paper, we ask: is the pay-per-task method the right one? We draw on behavioral economic research to examine whether payment in bulk after every ten tasks, saving money via coupons instead of earning money, or material goods rather than money will increase the number of completed tasks. We perform a twenty-day, between-subjects field experiment (N=300) on a mobile crowdsourcing application and measure how often workers responded to a task notification to fill out a short survey under each incentive condition. Task completion rates increased when paying in bulk after ten tasks: doing so increased the odds of a response by 1.4x, translating into 8% more tasks through that single intervention. Payment with coupons instead of money produced a small negative effect on task completion rates. Material goods were the most robust to decreasing participation over time.

PolicyKit: Building Governance in Online Communities

Abstract: The software behind online community platforms encodes a governance model that represents a strikingly narrow set of governance possibilities focused on moderators and administrators. When online communities desire other forms of government, such as ones that take many members? opinions into account or that distribute power in non-trivial ways, communities must resort to laborious manual effort. In this paper, we present PolicyKit, a software infrastructure that empowers online community members to concisely author a wide range of governance procedures and automatically carry out those procedures on their home platforms. We draw on political science theory to encode community governance into policies, or short imperative functions that specify a procedure for determining whether a user-initiated action can execute. Actions that can be governed by policies encompass everyday activities such as posting or moderating a message, but actions can also encompass changes to the policies themselves, enabling the evolution of governance over time. We demonstrate the expressivity of PolicyKit through implementations of governance models such as a random jury deliberation, a multi-stage caucus, a reputation system, and a promotion procedure inspired by Wikipedia's Request for Adminship (RfA) process.

Gui --- phooey!: the case for text input

Abstract: Information cannot be found if it is not recorded. Existing rich graphical application approaches interfere with user input in many ways, forcing complex interactions to enter simple information, requiring complex cognition to decide where the data should be stored, and limiting the kind of information that can be entered to what can fit into specific applications' data models. Freeform text entry suffers from none of these limitations but produces data that is hard to retrieve or visualize. We describe the design and implementation of Jourknow, a system that aims to bridge these two modalities, supporting lightweight text entry and weightless context capture that produces enough structure to support rich interactive presentation and retrieval of the arbitrary information entered.

Crowdsourcing and human computation: systems, studies and platforms

Abstract: Crowdsourcing and human computation are transforming human-computer interaction, and CHI has led the way. The seminal publication in human computation was initially published in CHI in 2004 [1], and the first paper investigating Mechanical Turk as a user study platform has amassed over one hundred citations in two years [5]. However, we are just beginning to stake out a coherent research agenda for the field. This workshop will bring together researchers in the young field of crowdsourcing and human computation and produce three artifacts: a research agenda for the field, a vision for ideal crowdsourcing platforms, and a group-edited bibliography. These resources will be publically disseminated on the web and evolved and maintained by the community.

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.