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

People use different size modifiers to refer to different object sizes; “the long table” is likely to be a different table from “the small table”. However, the details influencing the selection of size modifier have not yet been uncovered. When is something “long”, and when is something “small”? We introduce a connection between the visible dimensions of objects and the kinds of language people use to refer to them. First, we conduct an experiment to elicit size-denoting modifiers from images of real world objects. We find that we are able to effectively model the relationship between dimensional features and modifier choice using decision trees. The images are then used as input to an object segmentation algorithm, and we compare how well we can predict speakers’ behavior using the real world measurements of the pictured objects and the image pixel-based measurements. We find that real world measurements are the best predictors of modifier choice, suggesting that people infer real world size features from images. However, automatically extracted pixel measurements do perform relatively well at predicting modifier choice, offering a potential connection between computer vision and natural language. When speaker identity is taken into account, modifier choice can be predicted with even greater accuracy (around 75%), and the difference between automatically extracted and real world measurements is no longer significant.

Applying Machine Learning to the Choice of Size Modifiers

With the advent of Transformers, large language models (LLMs) have saturated well-known NLP benchmarks and leaderboards with high aggregate performance. However, many times these models systematically fail on tail data or rare groups not obvious in aggregate evaluation. Identifying such problematic data groups is even more challenging when there are no explicit labels (e.g., ethnicity, gender, etc.) and further compounded for NLP datasets due to the lack of visual features to characterize failure modes (e.g., Asian males, animals indoors, waterbirds on land, etc.). This paper introduces an interactive Systematic Error Analysis and Labeling (\seal) tool that uses a two-step approach to first identify high error slices of data and then, in the second step, introduce methods to give human-understandable semantics to those underperforming slices. We explore a variety of methods for coming up with coherent semantics for the error groups using language models for semantic labeling and a text-to-image model for generating visual features. SEAL toolkit and demo screencast is available at https://huggingface.co/spaces/nazneen/seal.

SEAL : Interactive Tool for Systematic Error Analysis and Labeling

Producing a fluent ordering for a set of prenominal modifiers in a noun phrase (NP) is a problematic task for natural language generation and machine translation systems. We present a novel approach to this issue, adapting multiple sequence alignment techniques used in computational biology to the alignment of modifiers. We describe two training techniques to create such alignments based on raw text, and demonstrate ordering accuracies superior to earlier reported approaches.

Prenominal Modifier Ordering via Multiple Sequence Alignment

Examples are generally directed towards automatic assessment of machine generated conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of multi-reference responses. A response in the set of multi-reference responses includes it context-message data pair and rating. The rating indicates a quality of the response relative to the context-message data pair. A response assessment engine generates a metric score for a machine-generated response based on an assessment metric and the set of multi-reference responses. The metric score indicates a quality of the machine-generated conversational response relative to a user-generated message and a context of the user-generated message. A response generation system of a computing device, such as a digital assistant, is optimized and adjusted based on the metric score to improve the accuracy, quality, and relevance of responses output to the user.

Metric for automatic assessment of conversational responses

In this paper, we argue that ordering prenominal modifiers -- typically pursued as a supervised modeling task -- is particularly well-suited to semi-supervised approaches. By relying on automatic parses to extract noun phrases, we can scale up the training data by orders of magnitude. This minimizes the predominant issue of data sparsity that has informed most previous approaches. We compare several recent approaches, and find improvements from additional training data across the board; however, none outperform a simple n-gram model.

/pdf/semi-supervised-modeling-for-prenominal-modifier-ordering-2fyd8ew18u.pdf

Margaret Mitchell

Papers

Applying Machine Learning to the Choice of Size Modifiers

SEAL : Interactive Tool for Systematic Error Analysis and Labeling

Prenominal Modifier Ordering via Multiple Sequence Alignment

Metric for automatic assessment of conversational responses

Semi-Supervised Modeling for Prenominal Modifier Ordering