文档章节

人工智能资料库:第29辑(20170210)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:19
字数 679
阅读 1
收藏 0

  1. 【博客】A Comprehensive Introduction to Word Vector Representations

简介:

Making a computer mimic the human cognitive function of understanding text is a really hot topic nowadays. Applications range from sentiment analysis to text summary and language translation among others. We call this field of computer science and artificial intelligence Natural Language Processing, or NLP (gosh, please don’t confuse with Neuro-linguistic Programming).

原文链接:https://medium.com/@baristaGeek/jkljlj-7d6e699895c4#.3can81wbt


2.【博客】Linear Regression Geometry

简介:

Linear Regression is one of the most widely used statistical model used in many situations.If we have Y variable which in continuous i.e. can take decimal values, and is expected to have linear relation with X variables, this relation could be modeled as linear regression, mostly the first model to fit,if we are planning to develop a model of forecasting Y or trying to build hypothesis about relation Xs on Y.

The general approch is to understand the theory based on principle of "minimum" square error and we derive the solution using minimization of functions through calculus,however it has a nice geometric intuition, if we use the tricks or methods related to solving an over-determined system

原文链接:http://www.datasciencecentral.com/profiles/blogs/linear-regression-geometry


3.【博客】Generating Large Images from Latent Vectors

简介:

In some domains of digital generative art, an artist would typically not work with an image editor directly to create an artwork. Typically, the artist would program a set of routines that would generate the actual images. These routines compose of instructions to tell the machine to draw lines and shapes at certain coordinates, and manipulate colours in some mathematically defined way. The final artwork, which may be presented as a pixellated image, or printed out on physical medium, can be entirely captured and defined by a set of mathematical routines.

Many natural images have interesting mathematical properties. Simple math functions have been written to generate natural fractal-like patterns such as tree branches and snowflakes. Like fractals, a simple set of mathematical rules can sometimes generate a highly complicated image that can be zoomed-in or zoomed-out indefinitely.

原文链接:http://blog.otoro.net/2016/04/01/generating-large-images-from-latent-vectors/


4.【论文】Adversarial Attacks on Neural Network Policies

简介:

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show that adversarial attacks are also effective when targeting neural network policies in reinforcement learning. Specifically, we show that existing adversarial example crafting techniques can be used to significantly degrade the test-time performance of trained policies. Our threat model considers adversaries capable of introducing small perturbations to the raw input of the policy. We characterize the degree of vulnerability across tasks and training algorithms, for a subclass of adversarial-example attacks in white-box and black-box settings. Regardless of the learned task or training algorithm, we observe a significant drop in performance, even with small adversarial perturbations that do not interfere with human perception.

原文链接:http://rll.berkeley.edu/adversarial/


5.【博客】Apple’s deep learning frameworks: BNNS vs. Metal CNN

简介:

With iOS 10, Apple introduced two new frameworks for doing deep learning on iOS: BNNS and MPSCNN.
BNNS, or bananas Basic Neural Network Subroutines, is part of the Accelerate framework, a collection of math functions that take full advantage of the CPU’s fast vector instructions.

MPSCNN is part of Metal Performance Shaders, a library of optimized compute kernels that run on the GPU instead of on the CPU.

So… as iOS developers we now have two APIs for deep learning that appear to do pretty much the same thing.
Which one should you pick?
In this blog post we’ll put BNNS and MPSCNN head-to-head to examine their differences. We also make both APIs take a speed test to see which is fastest.

原文链接:http://machinethink.net/blog/apple-deep-learning-bnns-versus-metal-cnn/


本文转载自:http://www.jianshu.com/p/e81e6854983a

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
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
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
【Java每日一题】20170210

20170209问题解析请点击今日问题下方的“【Java每日一题】20170210”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序输出结果是什么?(点击以下“【Java每日一题...

weknow
2017/02/10
0
0
CCF-GAIR 2018 第一批包机酒学生名单出炉!AI 科技评论请你来参加CCF-GAIR大会啦!

CCF - GAIR 2018 将于 6 月 29 日 至 7 月 1 日 在深圳举行。 三天议程及强大阵容已经陆续出炉。 6 月 8 日, 雷锋网旗下学术频道 AI 科技评论启动了 CCF-GAIR 2018 的免费门票申请通道, 并...

奕欣
06/16
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

没有更多内容

加载失败,请刷新页面

加载更多

5whys分析法在美团工程师中的实践

前言 网站的质量和稳定性对于用户和公司来说至关重要,但是在网站的快速发展过程中,由于各种原因导致事故不可避免的发生,这些大大小小的事故对公司难免会造成一些负面的影响,为了避免同类...

Skqing
29分钟前
2
0
Android 接收监听开机完成,并且开机自启动

1,定义一个广播接收者的类 ,并重写抽象方法 public class BootCompleteReceiver extends BroadcastReceiver 2,在Androidmanifest 注册 <receiver android:name=".receiver.BootCompleteRece......

lanyu96
32分钟前
2
0
小程序记录

1、button的边框、角等需要在伪元素after修改去除

originDu
35分钟前
1
0
微博什么技术啊……还说支持八个明星并发出轨,结果…

是的,大家可能都知道了,女神张靓颖结婚了。。 我去,写错了,是————赵丽颖。 为什么我头脑一瞬间出现的是张靓颖,作为一个码农,技术宅,拼音缩小都是 ZLY,博主我真有点傻傻分不清楚了...

Java技术栈
35分钟前
12
0
模块化

1,什么是模块化? 模块化是指将一个复杂的系统分解为多个模块,方便编码。 2,为什么要用模块化? 降低复杂性,降低代码耦合度,部署方便,提高效率。 3,模块化的好处? a,避免命名冲突,减少...

羊皮卷
35分钟前
2
0

没有更多内容

加载失败,请刷新页面

加载更多

返回顶部
顶部