# Tensorflow的逆置换操作函数tf.invert_permutation

tf.invert_permutation(x,name=None)计算序列的逆置换（inverse permutation）。本操作是计算张量的索引的逆置换。x是一维的整数张量，表示一个以0为开始的索引数组，然后根据这里元素的值来放入整数什，计算公式如下：y[x[i]] = i for i in [0, 1, ..., len(x) -1]从0开始，没有重复和负数值。例如:# 张量 `x` 是 ...

# MIT的《深度学习》精读（23）

MIT的《深度学习》精读（23）There are two main ways of measuring the depth of a model. The first view is based on the number of sequential instructions that must be executed to evaluate the architecture. We can t...

# 循环神经网络(RNN, Recurrent Neural Networks)的入门必学文章

http://colah.github.io/posts/2015-08-Understanding-LSTMs/http://www.csdn.net/article/2015-11-25/2826323循环神经网络(Recurrent Neural Networks，RNNs)已经在众多自然语言处理(Natural Language Processing, NLP)中取得了巨大成功以及广泛应用...

# MIT的《深度学习》精读（22）

The idea of learning the right representation for the data provides one perspective on deep learning. Another perspective on deep learning is that depth allows the computer to learn a multi-step compu...

# MIT的《深度学习》精读（21）

The quintessential example of a deep learning model is the feedforward deep network or multilayer perceptron (MLP). A multilayer perceptron is just a mathematical function mapping some set of input va...

# Windows下升级TensorFlow到1.0.1版本

TensorFlow 1.0.1Bug Fixes and Other ChangesChange GraphConstructor to not increase the version when importing, but instead take the min of all versions.Google Cloud Storage fixes.Removed tf.core and t...

# MIT的《深度学习》精读（20）

Deep learning solves this central problem in representation learning by introducing representations that are expressed in terms of other, simpler representations. Deep learning allows the computer to ...

# 使用Python来编写一个简单的感知机

https://blog.dbrgn.ch/2013/3/26/perceptrons-in-python/ 目前，我在HSR上参加了一个神经网络和机器学习的课程，其中学习到一个最简单的神经网络模型，就是感知机（perceptronperceptronperceptron）。 背景资料最简单的神经网络的模型就是感知机分类器，它有不同的输入（x1, x2,......xn)，然后有不同的权重值（w1...

# MIT的《深度学习》精读（19）

Of course, it can be very difficult to extract such high-level, abstract features from raw data. Many of these factors of variation, such as a speaker’s accent, can be identified only using sophistica...

# MIT的《深度学习》精读（18）

A major source of difficulty in many real-world artificial intelligence applications is that many of the factors of variation influence every single piece of data we are able to observe. The individua...

# 为什么现在深度学习才流行起来？

16条 共2页1 2 下一页 尾页
个人资料
• 访问：5594064次
• 积分：73134
• 等级：
• 排名：第25名
• 原创：1587篇
• 转载：61篇
• 译文：11篇
• 评论：2086条
 深入浅出Numpy 难度：初级 类型：技术教程
 Python游戏开发入门 难度：初级 类型：实战教学
 你也能动手修改C编译器 难度：初级 类型：实战教学
文章存档
阅读排行
最新评论
常用连接