銳眼視點(diǎn)：CNN 的基本原理是什么蚁鳖？發(fā)展歷史是怎樣的磺芭？有哪些應(yīng)用案例？醉箕；ChatBots 的發(fā)展如火如荼钾腺，面臨的挑戰(zhàn)有哪些？讥裤；共享經(jīng)濟(jì)模式下的車輛共享能否替代私家車放棒？。
TD 精選
卷積神經(jīng)網(wǎng)絡(luò)的直觀解釋
原文鏈接：An Intuitive Explanation of Convolutional Neural Networks
卷積神經(jīng)網(wǎng)絡(luò) (ConvNets or CNNs) 是在像圖像識(shí)別和分類領(lǐng)域證明了自己的神經(jīng)網(wǎng)絡(luò)的一個(gè)分類己英，而 CNN 更是在自然語(yǔ)言處理间螟、機(jī)器人智能以及自動(dòng)駕駛等領(lǐng)域得到廣泛使用。
文章作者對(duì) CNN 的基本概念和改進(jìn)歷史作了深入淺出的解釋损肛，并且提供了非常多高質(zhì)量的參考資料厢破，比如在總結(jié) CNN 發(fā)展史時(shí)，文中提到：
**LeNet (1990s): **Already covered in this article.
1990s to 2012: In the years from late 1990s to early 2010s convolutional neural network were in incubation. As more and more data and computing power became available, tasks that convolutional neural networks could tackle became more and more interesting.
**AlexNet (2012) – **In 2012, Alex Krizhevsky (and others) released AlexNet which was a deeper and much wider version of the LeNet and won by a large margin the difficult ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2012. It was a significant breakthrough with respect to the previous approaches and the current widespread application of CNNs can be attributed to this work.
ZF Net (2013) – The ILSVRC 2013 winner was a Convolutional Network from Matthew Zeiler and Rob Fergus. It became known as the ZFNet (short for Zeiler & Fergus Net). It was an improvement on AlexNet by tweaking the architecture hyperparameters.
**GoogLeNet (2014) – **The ILSVRC 2014 winner was a Convolutional Network from Szegedy et al.from Google. Its main contribution was the development of an Inception Module that dramatically reduced the number of parameters in the network (4M, compared to AlexNet with 60M).
VGGNet (2014) – The runner-up in ILSVRC 2014 was the network that became known as theVGGNet. Its main contribution was in showing that the depth of the network (number of layers) is a critical component for good performance.
**ResNets (2015) – **Residual Network developed by Kaiming He (and others) was the winner of ILSVRC 2015. ResNets are currently by far state of the art Convolutional Neural Network models and are the default choice for using ConvNets in practice (as of May 2016).
業(yè)界新聞
ChatBots 面臨的挑戰(zhàn)
原文鏈接：15% of all Google searches are unique, which is also a problem for chatbots
Facebook 在今年的 F8 大會(huì)上宣布 ChatBot 將會(huì)是未來(lái)的重點(diǎn)治拿，Slack 和 HipChat 上面也涌現(xiàn)出了各種各樣的 ChatBot摩泪，很多公司都在講自己的服務(wù) Bot 化到這些平臺(tái)。應(yīng)用開(kāi)發(fā)者劫谅，特別是 Bots 的創(chuàng)建者见坑，都在積極投入到聊天式接口的崛起中。但是自然語(yǔ)言處理——讓用戶像和真人聊天一樣和 Bots 交互的技術(shù)——還沒(méi)有讓客戶及其興奮捏检，因?yàn)檫@并不是一條容易的路荞驴。
Talla 在 Slack 平臺(tái)推出的 Task Assistant 產(chǎn)品擁有超過(guò) 700 家公司客戶。在經(jīng)過(guò)一段時(shí)間的運(yùn)營(yíng)以及和客戶的溝通后未檩，他們整理了下面的一些經(jīng)驗(yàn)：
- Lesson 1: Human language is extremely varied
- Lesson 2: You can’t just pass off the unclear use cases to a human
- Lesson 3: Map intent with contextual awareness
- Lesson 4: Sometimes, it’s the human’s ‘NLP’ that’s the problem
智能車共享服務(wù)可以取代私家車嗎戴尸？
原文鏈接：How A Smart Car-Sharing Service Is Taking Vehicles Off The Road In Cities
加州大學(xué)伯克利分校的 Transportation Sustainability Research Center 在一份 研究報(bào)告 中發(fā)現(xiàn)，一輛屬于 car2go ——一家 2009 年成立的提供共享智能車的德國(guó)公司——可以替代 7 到 11 輛私家車冤狡。
