人工智能资料库:第24辑(20170205)


  1. 【博客】How To Code Your Own Personal Assistant Using Python Programming

简介:

In this article, I’m sharing the efforts of a programmer to create his own python-powered personal assistant. Using open source libraries for text-to-speech conversion and speech recognition, he describes a way to create a personal “Jarvis”.

原文链接:https://fossbytes.com/code-personal-assistant-using-python-programming/


2.【博客】Asynchronous n-steps Q-learning

简介:

Q-leaning in the most famous Temporal Difference algorithm. Original Q-learning algorithm tries to determine the state-action value function that minimizes the error below.

原文链接:https://papoudakis.github.io/announcements/qlearning/


3.【代码】YouTube Like Count Predictor

简介:

This a tool for getting youtube video like count prediction.A Random Forest model was used for training on a large dataset of ~3,50,000 videos.Feature engineering,Data cleaning, Data selection and many other techniques were used for this task.

原文链接:https://github.com/ayush1997/YouTube-Like-predictor


4.【教程】Tutorial on Deep Learning

简介:

Lecture 1: Tutorial on Deep Learning I
Lecture 2: Tutorial on Deep Learning II 
Lecture 3: Tutorial on Deep Learning III
Lecture 4: Tutorial on Deep Learning IV 

Speaker: Ruslan Salakhutdinov, Carnegie Mellon University

原文链接:https://simons.berkeley.edu/talks/tutorial-deep-learning


5.【博客】Food Classification with Deep Learning in Keras / Tensorflow

简介:

3294481634_48b2b5baea_b.jpg

As an introductory project for myself, I chose to use a pre-trained image classifier that comes with Keras, and retrain it on a dataset that I find interesting. I’m very much into good food and home cooking, so something along those lines was appetizing.

In the paper, Food-101 – Mining Discriminative Components with Random Forests, they introduce the Food-101 dataset. There are 101 different classes of food, with 1000 labeled images per class available for supervised training.

原文链接:http://blog.stratospark.com/deep-learning-applied-food-classification-deep-learning-keras.html?utm_campaign=Revue%20newsletter&utm_medium=Newsletter&utm_source=revue


评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值