Automatic Speech Recognition: A Deep Learning Approach (Signals and Communication Technology): Dong Yu, Li Deng: 9781447157786:
This book provides a comprehensive overview of the recent advancement in the field of automatic speech recognition with a focus on deep learning models including deep neural networks and many of their variants. This is the first automatic speech recognition book dedicated to the deep learning approach. In addition to the rigorous mathematical treatment of the subject, the book also presents insights and theoretical foundation of a series of highly successful deep learning models.
相關推薦
Automatic Speech Recognition: A Deep Learning Approach (Signals and Communication Technology): Dong Yu, Li Deng: 9781447157786:
This book provides a comprehensive overview of the recent advancement in the field of automatic speech recognition with a focus on deep learn
論文閱讀 | DeepDrawing: A Deep Learning Approach to Graph Drawing
作者：Yong Wang, Zhihua Jin, Qianwen Wang, Weiwei Cui, Tengfei Ma and Huamin Qu 本文發表於VIS2019, 來自於香港科技大學的視覺化小組(屈華民教授領導)的研究 1. 簡介 圖資料廣泛用於各個領域，例如生物資訊學，金融和社交網路分析。
A Bayesian Approach to Deep Neural Network Adaptation with Applications to Robust Automatic Speech Recognition
機器學習 屬於 瓶頸 特征 oid ack enter 變換 表示 基於貝葉斯的深度神經網絡自適應及其在魯棒自動語音識別中的應用 直接貝葉斯DNN自適應 使用高斯先驗對DNN進行MAP自適應 為何貝葉斯在模型自適應中很有用？ 因為自適應問題可以視為後驗估計
『 論文閱讀』A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems
AbstractMULTI-VIEW-DNN聯合了多個域做的豐富特徵，使用multi-view DNN模型構建推薦，包括app、新聞、電影和TV，相比於最好的演算法，老使用者提升49%，新使用者提升110%。並且可以輕鬆的涵蓋大量使用者，解決冷啟動問題。主要做user embedding的過程，通多使用者在多
A Deep Learning-Based System for Vulnerability Detection(二)
接著上一篇，這篇研究實驗和結果。 A.用於評估漏洞檢測系統的指標 TP：為正確檢測到漏洞的樣本數量 FP：為檢測到虛假漏洞樣本的數量(誤報) FN：為未檢真實漏洞的樣本數量(漏報) TN：未檢測到漏洞樣本的數量 這篇文獻廣泛使用指標假陽性率(FPR),假陰性率(FNR),真陽性率或者召回率
A Deep Learning Based DDoS Detection System in Software-Defined Networking (SDN)
標題：基於深度學習的軟體定義網路（SDN）DDoS檢測系統 來源：Security and Safety 時間：2016年11月 摘要 分散式拒絕服務（DDoS）是當今組織網路基礎架構遇到的最普遍的攻擊之一。 本文在軟體定義網路（SDN）環境中提出了基於深度學習的多向量DDoS檢測系統。 SDN提供了針對
SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation論文解讀
一、論文概述 SenseGen這篇論文是17年發表在PerCom Workshops上的一篇論文，來自加州大學洛杉磯分校（University of California at Los Aneles，UCLA）網路與嵌入式系統實驗室（Netoworked & Embedded Syste
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
這篇文章來大致介紹一下ConvLSTM的基本原理和應用場景。個人認為有時候對於一個演算法改進很大程度上會受到應用場景的啟示，比如現在要說的這篇。不知道論文作者當時想到這個idea時是不是也是這樣。 1.論文的核心思想 先來想象一下這麼一個應用場景：根據某個城市歷史的降雨量資
The AI Paradox: How A Deep Learning Startup Is Building Successful AI Solutions
We have a paradox staring us in the face. All that web content creates a great forum for philosophical debate: Will AI save the world or bring about the ex
Building A Deep Learning Model using Keras
Building A Deep Learning Model using KerasDeep learning is an increasingly popular subset of machine learning. Deep learning models are built using neural
How to build a Deep Learning Image Classifier for Game of Thrones dragons
Performance of most flavors of the old generations of learning algorithms will plateau. Deep learning, training large neural networks, is scalable and perf
How to Develop a Deep Learning Photo Caption Generator from Scratch
Tweet Share Share Google Plus Develop a Deep Learning Model to Automatically Describe Photograph
學習摘要：convolutional-lstm-network-a-machine-learning-approach-for-precipitation-nowcasting
原文： convolutional-lstm-network-a-machine-learning-approach-for-precipitation-nowcasting 部落格內容： 關於該文章的學習摘要 將論文的關鍵內容進行了翻譯、配圖說明，配合原文閱讀，應該
【Person Re-ID】Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
Introduction Person Re-ID目前依然是一項十分具有挑戰的任務。姿勢，視角，光照，背景和遮擋都給這項任務帶來困難。 傳統的方法通過學習low-level特徵，比如顏色、外形、區域性描述子等來描述一個人。而CNN通過學習high-lev
【論文筆記】Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
摘要 Person re-identification (ReID) is an important task in computer vision. Recently, deep learning with a metric learning loss has becom
Amazon Transcribe – Automatic Speech Recognition
Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capability to their app
16 On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima 1609.04836v1
Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, Ping Tak Peter TangNorthwestern University & Intel* SGD及其變種在batch size增大
Distributed deep learning with Horovod and PowerAI DDL
Horovod is a popular distributed training framework for TensorFlow, Keras, and PyTorch. This blog post explains how to use the efficient PowerAI DDL com
《On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima》-ICLR2017文章閱讀
這是一篇發表在ICLR2017上面的文章。 這篇文章探究了深度學習中一個普遍存在的問題——使用大的batchsize訓練網路會導致網路的泛化效能下降（文中稱之為Generalization Gap）。文中給出了Generalization Gap現象的解釋：大
《A Discriminative Feature Learning Approach for Deep Face Recognition》論文筆記
1. 論文思想 在這篇文章中尉人臉識別提出了一種損失函式，叫做center loss，在網路中加入該損失函式之後可以使得網路學習每類特徵的中心，懲罰每類的特徵與中心之間的距離。並且該損失函式是可訓練的，並且在CNN中容易優化。那麼，將center loss與softmax相結合會增加