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.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

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

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 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.

Deep Learning

Crowdsourcing systems accomplish large tasks with scale and speed by breaking work down into independent parts. However, many types of complex creative work, such as fiction writing, have remained out of reach for crowds because work is tightly interdependent: changing one part of a story may trigger changes to the overall plot and vice versa. Taking inspiration from how expert authors write, we propose a technique for achieving interdependent complex goals with crowds. With this technique, the crowd loops between reflection, to select a high-level goal, and revision, to decompose that goal into low-level, actionable tasks. We embody this approach in Mechanical Novel, a system that crowdsources short fiction stories on Amazon Mechanical Turk. In a field experiment, Mechanical Novel resulted in higher-quality stories than an iterative crowdsourcing workflow. Our findings suggest that orienting crowd work around high-level goals may enable workers to coordinate their effort to accomplish complex work.

Mechanical Novel: Crowdsourcing Complex Work through Reflection and Revision

In online communities, antisocial behavior such as trolling disrupts constructive discussion. While prior work suggests that trolling behavior is confined to a vocal and antisocial minority, we demonstrate that ordinary people can engage in such behavior as well. We propose two primary trigger mechanisms: the individual's mood, and the surrounding context of a discussion (e.g., exposure to prior trolling behavior). Through an experiment simulating an online discussion, we find that both negative mood and seeing troll posts by others significantly increases the probability of a user trolling, and together double this probability. To support and extend these results, we study how these same mechanisms play out in the wild via a data-driven, longitudinal analysis of a large online news discussion community. This analysis reveals temporal mood effects, and explores long range patterns of repeated exposure to trolling. A predictive model of trolling behavior shows that mood and discussion context together can explain trolling behavior better than an individual's history of trolling. These results combine to suggest that ordinary people can, under the right circumstances, behave like trolls.

/pdf/anyone-can-become-a-troll-causes-of-trolling-behavior-in-1ojxvpz3eq.pdf

Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions

We present Collabio, a social tagging game within an online social network that encourages friends to tag one another. Collabio's approach of incentivizing members of the social network to generate information about each other produces personalizing information about its users. We report usage log analysis, survey data, and a rating exercise demonstrating that Collabio tags are accurate and augment information that could have been scraped online.

/pdf/collabio-a-game-for-annotating-people-within-social-networks-41r9hjf7pb.pdf

Collabio: a game for annotating people within social networks

Crowdsourcing systems lack effective measures of the effort required to complete each task. Without knowing how much time workers need to execute a task well, requesters struggle to accurately structure and price their work. Objective measures of effort could better help workers identify tasks that are worth their time. We propose a data-driven effort metric, ETA (error-time area), that can be used to determine a task's fair price. It empirically models the relationship between time and error rate by manipulating the time that workers have to complete a task. ETA reports the area under the error-time curve as a continuous metric of worker effort. The curve's 10th percentile is also interpretable as the minimum time most workers require to complete the task without error, which can be used to price the task. We validate the ETA metric on ten common crowdsourcing tasks, including tagging, transcription, and search, and find that ETA closely tracks how workers would rank these tasks by effort. We also demonstrate how ETA allows requesters to rapidly iterate on task designs and measure whether the changes improve worker efficiency. Our findings can facilitate the process of designing, pricing, and allocating crowdsourcing tasks.

/pdf/measuring-crowdsourcing-effort-with-error-time-curves-5ant0foija.pdf

Measuring Crowdsourcing Effort with Error-Time Curves

Visual knowledge bases such as Visual Genome power numerous applications in computer vision, including visual question answering and captioning, but suffer from sparse, incomplete relationships. All scene graph models to date are limited to training on a small set of visual relationships that have thousands of training labels each. Hiring human annotators is expensive, and using textual knowledge base completion methods are incompatible with visual data. In this paper, we introduce a semi-supervised method that assigns probabilistic relationship labels to a large number of unlabeled images using few labeled examples. We analyze visual relationships to suggest two types of image-agnostic features that are used to generate noisy heuristics, whose outputs are aggregated using a factor graph-based generative model. With as few as 10 labeled examples per relationship, the generative model creates enough training data to train any existing state-of-the-art scene graph model. We demonstrate that our method outperforms all baseline approaches on scene graph prediction by 5.16 recall@100 for PREDCLS. In our limited label setting, we define a complexity metric for relationships that serves as an indicator (R^2 = 0.778) for conditions under which our method succeeds over transfer learning, the de-facto approach for training with limited labels.

Michael S. Bernstein

Papers

Mechanical Novel: Crowdsourcing Complex Work through Reflection and Revision

Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions

Collabio: a game for annotating people within social networks

Measuring Crowdsourcing Effort with Error-Time Curves

Scene Graph Prediction with Limited Labels.