摘要算法

重點 (Top highlight)

This post reviews the latest innovations of TCN based solutions. We first present a case study of motion detection and briefly review the TCN architecture and its advantages over conventional approaches such as Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN). Then, we introduce several novels using TCN, including improving traffic prediction, sound event localization & detection, and probabilistic forecasting.

這篇文章回顧了基于TCN的解決方案的最新創(chuàng)新。 我們首先介紹運動檢測的案例研究，并簡要回顧TCN架構(gòu)及其相對于傳統(tǒng)方法(如卷積神經(jīng)網(wǎng)絡(luò)(CNN)和遞歸神經(jīng)網(wǎng)絡(luò)(RNN))的優(yōu)勢。 然后，我們介紹了使用TCN的幾本小說，包括改善交通預測，聲音事件定位和檢測以及概率預測。

A brief review of TCN

TCN簡要回顧

The seminal work of Lea et al. (2016) first proposed a Temporal Convolutional Networks (TCNs) for video-based action segmentation. The two steps of this conventional process include: firstly, computing of low-level features using (usually) CNN that encode spatial-temporal information and secondly, input these low-level features into a classifier that captures high-level temporal information using (usually) RNN. The main disadvantage of such an approach is that it requires two separate models. TCN provides a unified approach to capture all two levels of information hierarchically.

Lea等人的開創(chuàng)性工作。 (2016)首先提出了基于視頻的動作分割的時間卷積網(wǎng)絡(luò)(TCN)。 此常規(guī)過程的兩個步驟包括：首先，使用(通常)對時空信息進行編碼的CNN計算低級特征，其次，將這些低級特征輸入到使用(通常是)捕獲高級時空信息的分類器中)RNN。 這種方法的主要缺點是需要兩個單獨的模型。 TCN提供了一種統(tǒng)一的方法來分層捕獲所有兩個級別的信息。

The encoder-decoder framework is presented in Fig.1, where further information regarding the architecture can be found in the first two references (at the end of the post). The most critical issues are provided as follows: TCN can take a series of any length and output it as the same length. A causal convolutional is used where a 1D fully convolutional network architecture is used. A key characteristic is that the output at time t is only convolved with the elements that occurred before t.

編碼器-解碼器框架如圖1所示，其中有關(guān)體系結(jié)構(gòu)的更多信息可以在前兩個參考文獻中找到(在文章末尾)。 提供了最關(guān)鍵的問題，如下所示：TCN可以采用一系列任意長度并將其輸出為相同長度。 在使用一維完全卷積網(wǎng)絡(luò)體系結(jié)構(gòu)的情況下，使用因果卷積。 一個關(guān)鍵特征是，時間t的輸出僅與t之前發(fā)生的元素卷積。

The buzz around TCN arrives even to Nature journal, with the recent publication of the work by Yan et al. (2020) on TCN for weather prediction tasks. In their work, a comparative experiment was conducted with TCN and LSTM. One of their results was that, among other approaches, the TCN performs well in prediction tasks with time-series data.

隨著Yan等人最近發(fā)表的研究成果，圍繞TCN的話題甚至傳到了《自然》雜志上。 (2020)在TCN上進行天氣預報任務(wù)。 在他們的工作中，使用TCN和LSTM進行了對比實驗。 他們的結(jié)果之一是，除其他方法外，TCN在使用時序數(shù)據(jù)的預測任務(wù)中表現(xiàn)出色。

Yan et al. (2020)嚴等。 (2020年)

The next sections provide the implementation and extension of this classical TCN.

下一節(jié)提供了此經(jīng)典TCN的實現(xiàn)和擴展。

Improving traffic prediction

改善流量預測

Ridesharing and online navigation services can improve traffic prediction and change the way of life on the road. Fewer traffic jams, less pollution, safe and fast driving are just a few examples of essential issues that can be achieved by better traffic predictions. As this is a real-time data-driven problem, it is necessary to utilize the accumulated data of upcoming traffic. For this reason, Dai et al. (2020) recently presented a Hybrid Spatio-Temporal Graph Convolutional Network (H-STGCN). The general idea is to take the advantages of the piecewise-liner-flow-density relationship and convert the upcoming traffic volume in its equivalent in travel time. One of the most interesting approaches they used in this work is the graph convolution to capture the spatial dependency. The compound adjacency matrix captures the innate characteristics of traffic approximation (for more information, please see Li, 2017). In the following architecture, four modules are presented to describe the entire prediction process.

拼車和在線導航服務(wù)可以改善交通預測并改變道路上的生活方式。 更少的交通擁堵，更少的污染，安全和快速的駕駛只是通過更好的交通預測可以實現(xiàn)的基本問題的幾個例子。 由于這是實時數(shù)據(jù)驅(qū)動的問題，因此有必要利用即將到來的流量的累積數(shù)據(jù)。 由于這個原因，Dai等。 (2020)最近提出了一種混合時空圖卷積網(wǎng)絡(luò)(H-STGCN)。 總體思路是利用分段襯里流量密度關(guān)系的優(yōu)勢，并將即將來臨的交通量轉(zhuǎn)換為等效的行進時間。 他們在這項工作中使用的最有趣的方法之一是圖卷積以捕獲空間依賴性。 復合鄰接矩陣捕獲流量近似的固有特征(更多信息，請參見Li，2017)。 在以下架構(gòu)中，提出了四個模塊來描述整個預測過程。

Dai et al. (2020)戴等。 (2020年)

Sound event localization & detection

聲音事件定位和檢測

The field of sound event localization and detection (SELD) continues to grow. Understanding the environment plays a critical role in autonomous navigation. Guirguis et al. (2020) recently proposed a novel architecture for sound events SELD-TCN. They claim that their framework outperforms the state-of-the-art in the field, with faster training time. In their SELDnet (architecture below), a multichannel audio recording, sampled at 44.1 kHz, extracts, by applying a short-time Fourier transformation, the phase and magnitude of the spectrum, and stacks it as separate input features. Then, convolutional blocks and recurrent blocks (bi-directional GRUs) are connected, followed by a fully-connected block. The output of the SELDnet is the SOUND Event Detection (SED) and Direction Of Arrival (DOA).

聲音事件定位和檢測(SELD)的領(lǐng)域繼續(xù)增長。 了解環(huán)境在自主導航中起著至關(guān)重要的作用。 Guirguis等。 (2020)最近提出了一種聲音事件SELD-TCN的新穎架構(gòu)。 他們聲稱，他們的框架在現(xiàn)場培訓方面比當前最先進的技術(shù)領(lǐng)先。 在他們的SELDnet(以下結(jié)構(gòu))中，以44.1 kHz采樣的多通道音頻記錄通過應(yīng)用短時傅立葉變換提取頻譜的相位和幅度，并將其堆疊為單獨的輸入特征。 然后，連接卷積塊和循環(huán)塊(雙向GRU)，然后連接完全連接的塊。 SELDnet的輸出是聲音事件檢測(SED)和到達方向(DOA)。

Guirguis et al. (2020)Guirguis等。 (2020年)

In order to outperform it, they present the SELD-TCN:

為了超越它，他們提出了SELD-TCN：

Guirguis et al. (2020)Guirguis等。 (2020年)

As the dilated convolutions enable the net to process a variety of inputs, a more in-depth network may be required (which will be affected by unstable gradients during backpropagation). They overcome this challenge by adapting the WaveNet (Dario et al., 2017) architecture. They showed that the recurrent layers are not required for SELD tasks, and successfully detected the start and the end times of active sound events.

由于擴張的卷積使網(wǎng)絡(luò)能夠處理各種輸入，因此可能需要更深入的網(wǎng)絡(luò)(在反向傳播期間，網(wǎng)絡(luò)會受到不穩(wěn)定梯度的影響)。 他們通過適應(yīng)WaveNet(Dario et al。，2017)架構(gòu)克服了這一挑戰(zhàn)。 他們表明SELD任務(wù)不需要循環(huán)層，并成功檢測到活動聲音事件的開始和結(jié)束時間。

Probabilistic forecasting

概率預測

A novel framework designed by Chen et al. (2020) can be applied to estimate probability density. Time series prediction improves many business decision-making scenarios (for example, resources management). Probabilistic forecasting can extract information from historical data and minimize the uncertainty of future events. When the prediction task is to predict millions of related data series (as in the retail business), it requires prohibitive labor and computing resources for parameter estimation. In order to solve these difficulties, they proposed a CNN-based density estimation and prediction framework. Their framework can learn the latent correlation among series. The novelty in their work is the deep TCN they proposed, as presented in their architecture:

由Chen等人設(shè)計的新穎框架。 (2020)可用于估計概率密度。 時間序列預測改善了許多業(yè)務(wù)決策方案(例如，資源管理)。 概率預測可以從歷史數(shù)據(jù)中提取信息，并最大限度地減少未來事件的不確定性。 當預測任務(wù)要預測數(shù)百萬個相關(guān)數(shù)據(jù)序列時(如在零售業(yè)務(wù)中)，它需要大量的勞動力和計算資源來進行參數(shù)估計。 為了解決這些困難，他們提出了一種基于CNN的密度估計和預測框架。 他們的框架可以學習系列之間的潛在關(guān)聯(lián)。 他們的工作中的新穎之處在于他們提出的深層TCN，如其體系結(jié)構(gòu)所示：

Chen et al. (2020)Chen等。 (2020年)

The encoder-decoder modules solution might help in the design of practical large-scale applications.

編碼器-解碼器模塊解決方案可能有助于實際的大規(guī)模應(yīng)用設(shè)計。

摘要 (Summary)

In this post, we presented recent works that involve the temporal convolutional network and outperform classical CNN, and RNN approaches for time series tasks. For further information, please feel free to email me.

在這篇文章中，我們介紹了涉及時間卷積網(wǎng)絡(luò)并優(yōu)于經(jīng)典CNN的最新作品，以及用于時間序列任務(wù)的RNN方法。 有關(guān)更多信息，請隨時給我發(fā)送電子郵件。

— — — — — — — — — — — — — — — — — — — — — — — — —

— — — — — — — — — — — — — — — — — — — — — — — — — — — —

Visit my personal website: www.Barakor.com

訪問我的個人網(wǎng)站： www.Barakor.com

Linkedin https://www.linkedin.com/in/barakor/

Linkedin https://www.linkedin.com/in/barakor/

Twitter: BarakOr2

推特：BarakOr2

— — — — — — — — — — — — — — — — — — — — — — — — —

— — — — — — — — — — — — — — — — — — — — — — — — — — — —

翻譯自: https://towardsdatascience.com/temporal-convolutional-networks-the-next-revolution-for-time-series-8990af826567

摘要算法

總結(jié)

以上是生活随笔為你收集整理的摘要算法_摘要的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。