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

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

We propose a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. Our approach – Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any target concept (say logits for ‘dog’ or even a caption), flowing into the final convolutional layer to produce a coarse localization map highlighting the important regions in the image for predicting the concept. Unlike previous approaches, Grad- CAM is applicable to a wide variety of CNN model-families: (1) CNNs with fully-connected layers (e.g. VGG), (2) CNNs used for structured outputs (e.g. captioning), (3) CNNs used in tasks with multi-modal inputs (e.g. visual question answering) or reinforcement learning, without architectural changes or re-training. We combine Grad-CAM with existing fine-grained visualizations to create a high-resolution class-discriminative visualization, Guided Grad-CAM, and apply it to image classification, image captioning, and visual question answering (VQA) models, including ResNet-based architectures. In the context of image classification models, our visualizations (a) lend insights into failure modes of these models (showing that seemingly unreasonable predictions have reasonable explanations), (b) outperform previous methods on the ILSVRC-15 weakly-supervised localization task, (c) are more faithful to the underlying model, and (d) help achieve model generalization by identifying dataset bias. For image captioning and VQA, our visualizations show even non-attention based models can localize inputs. Finally, we design and conduct human studies to measure if Grad-CAM explanations help users establish appropriate trust in predictions from deep networks and show that Grad-CAM helps untrained users successfully discern a ‘stronger’ deep network from a ‘weaker’ one even when both make identical predictions. Our code is available at https: //github.com/ramprs/grad-cam/ along with a demo on CloudCV [2] and video at youtu.be/COjUB9Izk6E.

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to automatically learn to fix its gaze on salient objects while generating the corresponding words in the output sequence. We validate the use of attention with state-of-the-art performance on three benchmark datasets: Flickr9k, Flickr30k and MS COCO.

/pdf/show-attend-and-tell-neural-image-caption-generation-with-2atzmg08ji.pdf

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). 
The SqueezeNet architecture is available for download here: this https URL

/pdf/squeezenet-alexnet-level-accuracy-with-50x-fewer-parameters-175af9qwgu.pdf

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

This paper offers a solution to a small problem within a much larger problem. We focus on modelling how people use size in reference, words like "big" and "tall", which is one piece within the much larger problem of how people refer to visible objects. Examining size in isolation allows us to begin untangling a few of the complex and interacting features that affect reference, and we isolate a set of features that may be used in a hand-coded algorithm or a machine learning approach to generate one of six basic size types. The hand-coded algorithm generates a modifier type with a high correspondence to those observed in human data, and achieves 81.3% accuracy in an entirely new domain. This trails oracle accuracy for this task by just 8%. Features used by the hand-coded algorithm are added to a larger set of features in the machine learning approach, and we do not find a statistically significant difference between the precision and recall of the two systems. The input and output of these systems are a novel characterization of the factors that affect referring expression generation, and the methods described here may serve as one building block in future work connecting vision to language.

Two Approaches for Generating Size Modifiers

Researchers and practitioners from different disciplines have highlighted the ethical and legal challenges posed by the use of machine learned models and data-driven systems, and the potential for such systems to discriminate against certain population groups, due to biases in algorithmic decision-making systems. This tutorial aims to present an overview of algorithmic bias / discrimination issues observed over the last few years and the lessons learned, key regulations and laws, and evolution of techniques for achieving fairness in machine learning systems. We will motivate the need for adopting a “fairness-first” approach (as opposed to viewing algorithmic bias / fairness considerations as an afterthought), when developing machine learning based models and systems for different consumer and enterprise applications. Then, we will focus on the application of fairness-aware machine learning techniques in practice, by highlighting industry best practices and case studies from different technology companies. Based on our experiences in industry, we will identify open problems and research challenges for the data mining / machine learning community.

Fairness-Aware Machine Learning: Practical Challenges and Lessons Learned

Mobile and location-based social media applications provide platforms for users to share brief opinions about products, venues, and services. These quickly typed opinions, or micro-reviews, are a valuable source of current sentiment on a wide variety of subjects. However, there is currently little research on how to mine this information to present it back to users in easily consumable way. In this paper, we introduce the task of microsummarization, which combines sentiment analysis, summarization, and entity recognition in order to surface key content to users. We explore unsupervised and supervised methods for this task, and find we can reliably extract relevant entities and the sentiment targeted towards them using crowd-sourced labels as supervision. In an end-to-end evaluation, we find our best-performing system is vastly preferred by judges over a traditional extractive summarization approach. This work motivates an entirely new approach to summarization, incorporating both sentiment analysis and item extraction for modernized, at-a-glance presentation of public opinion.

/pdf/microsummarization-of-online-reviews-an-experimental-study-1jqkz324pt.pdf

Microsummarization of online reviews: an experimental study

We are pleased to present this special issue of IJCV on combined image and language understanding. It contains some of the latest work in a long line of research into problems at the intersection of computer vision and natural language processing. Research on language and vision has been stimulated by recent advances in object recognition. While multi-layer (or “deep”)models have been applied formore than twenty years (Lawrence et al. 1997; LeCun et al. 1989; Nowlan and Platt 1995), recently they have been shown to be extremely effective at large-vocabulary object recognition (Krizhevsky et al. 2012) and at text generation (Mikolov et al. 2010). The next logical step was to combine these two tasks to enable image captioning: generating a short language description based on an image (Kulkarni et al. 2013; Mitchell et al. 2012). In 2015, deep models produced state-of-the-art results in image captioning (Donahue et al. 2015; Fang et al. 2015; Karpathy and Fei-Fei 2015; Vinyals et al. 2015). These results were facilitated by the MSCOCO data set, which provided multiple crowd-sourced labels for thousands of images (Lin et al. 2014). The success of deep image captioning initially seemed promising. Had we finally solved combined image and language understanding?A closer inspection, however, revealed that suchunderstandingwas far fromsolved:Approaches that

/pdf/guest-editorial-image-and-language-understanding-3265qjunze.pdf

Guest Editorial: Image and Language Understanding

This document provides an overview of the Text Analysis Conference 2013 Knowledge Base Population Sentiment Slot Filling (SSF) track. Sentiment Slot Filling was a new task added this year, and pushed the state of the art in sentiment by requiring teams to provide sentiment analysis in open domains across a variety of genres. The task focused on identifying the polarity of sentiment as well as sentiment holders and sentiment targets.

/pdf/overview-of-the-tac2013-knowledge-base-population-evaluation-3v1mm7wxcq.pdf

Margaret Mitchell

Papers

Two Approaches for Generating Size Modifiers

Fairness-Aware Machine Learning: Practical Challenges and Lessons Learned

Microsummarization of online reviews: an experimental study

Guest Editorial: Image and Language Understanding

Overview of the TAC2013 Knowledge Base Population Evaluation: English Sentiment Slot Filling.