文档章节

人工智能资料库:第27辑(20170208)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:18
字数 615
阅读 1
收藏 0

  1. 【博客】DeepMind’s PathNet: A Modular Deep Learning Architecture for AGI

简介:


PathNetis a new Modular Deep Learning (DL) architecture, brought to you by who else but DeepMind, that highlights the latest trend in DL research to meldModular Deep Learning,Meta-Learningand Reinforcement Learning into a solution that leads to more capable DL systems. A January 20th, 2017 submitted Arxiv paper “PathNet: Evolution Channels Gradient Descent in Super Neural Networks” (Fernando et. al) has in its abstract the following interesting description of the work:

原文链接:https://medium.com/intuitionmachine/pathnet-a-modular-deep-learning-architecture-for-agi-5302fcf53273#.9uwk331d5


2.【博客】On the intuition behind deep learning & GANs—towards a fundamental understanding

简介:

A generative adversarial network (GAN) is composed of two separate networks - the generator and the discriminator. It poses the unsupervised learning problem as a game between the two. In this post we will see why GANs have so much potential, and frame GANs as a boxing match between two opponents.

原文链接:https://hackernoon.com/introduction-to-gans-a-boxing-match-b-w-neural-nets-b4e5319cc935#.lyaaodaih


3.【代码】nmtpy

简介:

nmtpyis a suite of Python tools, primarily based on the starter code provided indl4mt-tutorialfor training neural machine translation networks using Theano.

The basic motivation behind forkingdl4mt-tutorialwas to create a framework where it would be easy to implement a new model by just copying and modifying an existing model class (or even inheriting from it and overriding some of its methods).

原文链接:https://github.com/lium-lst/nmtpy


4.【博客】Demystifying Word2Vec

简介:

Research into word embeddings is one of the most interesting in the deep learning world at the moment, even though they were introduced as early as 2003 by Bengio, et al. Most prominently among these new techniques has been a group of related algorithm commonly referred to as Word2Vec which came out of google research.[^2]

In this post we are going to investigate the significance of Word2Vec for NLP research going forward and how it relates and compares to prior art in the field. In particular we are going to examine some desired properties of word embeddings and the shortcomings of other popular approaches centered around the concept of a Bag of Words (henceforth referred to simply as Bow) such as Latent Semantic Analysis. This shall motivate a detailed exposition of how and why Word2Vec works and whether the word embeddings derived from this method can remedy some of the shortcomings of BoW based approaches. Word2Vec and the concept of word embeddings originate in the domain of NLP, however as we shall see the idea of words in the context of a sentence or a surrounding word window can be generalized to any problem domain dealing with sequences or sets of related data points.

原文链接:http://www.deeplearningweekly.com/blog/demystifying-word2vec


5.【博客】Highlights and tutorials for concepts discussed in "Richard Socher on the future of deep learning"

简介:


Bruner, Jon. “The O’Reilly Bots Podcast” Audio blog post. Richard Socher on the Future of Deep Learning. O’Reilly, December 1, 2016.

Raw interview: I highly encourage listening to the podcast because the questions were so well crafted.

TLDR; Richard Socher of Salesforce (formerly Stanford and MetaMind) offers insight into the current and future states of deep learning used for NLP. We need one model that can do lot’s of different tasks and need to be wary of bias in our models. Future of conversational bots is multimodal and Salesforce research is awesome.

Disclaimer: This is my interpretation of the interview. I have included the pertinent questions I found interesting.

原文链接:https://theneuralperspective.com/2016/12/20/highlights-and-tutorials-for-concepts-discussed-in-richard-socher-on-the-future-of-deep-learning/


本文转载自:http://www.jianshu.com/p/36abd9278695

共有 人打赏支持
AllenOR灵感
粉丝 10
博文 2634
码字总数 82983
作品 0
程序员
预测流行偏好,时尚 AI 未来可望取代造型师

【Technews科技新报】预测时尚潮流是一项需要天分的工作,还得仰赖一个庞大的系统让少数人追捧的时尚进入大众流行市场,进而让业者赚取大笔钞票。现在预测工作也可以交给人工智能,让服饰业者...

黄 嬿
2017/12/26
0
0
依图夺脸部辨识首奖,施密特:美国 AI 优势只剩 5 年

Thomson Reuters 28 日报导,根据美国智库“新美国安全中心”(CNAS)专家 Elsa Kania 发布的报告,中国在科技领域已经不比美国差,可能已有能力在人工智能(AI)项目超越美国。 Alphabet I...

moneydj
2017/11/29
0
0
人工智能知识整理-第1辑(20170603)-机器学习入门资源汇总

有一天我忽然忘记了一个函数的用法,于是就上谷歌搜,结果搜出来的竟然是自己写的一篇笔记,上面有很详细的回答。当时感觉是跟另外一个自己进行交流,那一个是刚学完知识,印象还非常深的自己...

人工智豪
2017/06/03
0
0
柯洁又一次输了人机大战:不敌国产AI 直言太无力

▼ 点击上方蓝字 关注网易智能 为你解读AI领域大公司大事件,新观点新应用 【网易智能讯 4月28日消息】昨日,第一届“吴清源杯”世界女子围棋赛暨2018世界人工智能围棋大赛在福州举行,中国知...

mcil9g4065q
04/28
0
0
第27届日本IT周春季展将于5月在东京举办

第27届日本IT Week Spring是日本最大的综合性IT展会。本次展会由Reed Exhibitions Japan Ltd.来主办。Reed Exhibitions Japan Ltd. 成立于 1986 年,是领先全球的展览会主办机构- Reed Exhi...

玄学酱
05/01
0
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

kernel version does not match DSO version

错误信息: kernel version 384.11 does not match DSO version 384.130.0 原因是: cuda driver版本太低,不匹配DSO 简单有效的修复方法,升级nvidia driver, 步骤如下: 1. google seach ...

刘小米
今天
0
0
maven坐标和依赖

一、maven坐标详解 <groupId>com.fgt.club</groupId><artifactId>club-common-service-facade</artifactId><version>3.0.0</version><packaging>jar</packaging> maven的坐标元素说......

老韭菜
今天
1
0
springmvc-servlet.xml配置表功能解释

问:<?xml version="1.0" encoding="UTF-8" ?> 答: xml version="1.0"表示是此xml文件的版本是1.0 encoding="UTF-8"表示此文件的编码方式是UTF-8 问:<!DOCTYPE beans PUBLIC "-//SPRING//......

隐士族隐逸
今天
1
0
基于TP5的微信的公众号获取登录用户信息

之前讲过微信的公众号自动登录的菜单配置,这次记录一下在TP5项目中获取自动登录的用户信息并存到数据库的操作 基本的流程为:微信设置自动登录的菜单—>访问的URL指定的函数里获取用户信息—...

月夜中徘徊
今天
0
0
youTrack

package jetbrains.teamsys.license.runtime; 计算lis package jetbrains.ring.license.reader; 验证lis 安装后先不要生成lis,要把相关文件进行替换 ring-license-checker-1.0.41.jar char......

max佩恩
今天
2
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

返回顶部
顶部