Playing around with the linear perceptron algorithm

Playing around with the linear perceptron algorithm

Now, let generate a collection of points and then paint them according to a line. If the points are above the line, they are blue, if they are below, green.

IDENTIFYING MOST COMMON NBA PLAYERS FROM THE 2017 DRAFT CLASS USING PCA DIMENSIONALITY REDUCTION AND K NEAREST NEIGHBORS ALGORITHM

IDENTIFYING MOST COMMON NBA PLAYERS FROM THE 2017 DRAFT CLASS USING PCA DIMENSIONALITY REDUCTION AND K NEAREST NEIGHBORS ALGORITHM

The approach is pretty straightforward, and is outlined below before digging into all of the code.

Table of Contents

Table of Contents

Simulation strategy presented here is as in the original publication

Picasso Demo

Picasso Demo

Download devstack.

Introduction to Cloud Machine Learning with Flask API and CNTK

Introduction to Cloud Machine Learning with Flask API and CNTK

Here we present an overview of the application. The main procedure is executed by the CNTK CNN. The network is a pretrained ResNet with 152 layers . The CNN was trained on ImageNet dataset , which contains 1.2 million images ...

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Using functional programming in Python like a boss: Generators, Iterators and Decorators

Using functional programming in Python like a boss: Generators, Iterators and Decorators

When you write:

Do the same but with 1 more hidden layer

Do the same but with 1 more hidden layer

Delivered by Fastly , Rendered by Rackspace

Deep Q-learning

Deep Q-learning

We can simulate this game using OpenAI Gym . First, let's check out how OpenAI Gym works. Then, we'll get into training an agent to play the Cart-Pole game.

Generative Adversarial Networks

Generative Adversarial Networks

The weights will be initiliased using the Xavier initialisation method [1]. In this case, this is just a Gaussian distribution with a custom standard deviation: the standard deviation is inversely proportional to the number of neurons feeding into the neuron.

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Getting Started

Getting Started

In this notebook, we'll be explaining generative adversarial networks, and how you can use them to create a generator network that can create realistic MNIST digits through Tensorflow

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Appendix F - Introduction to NumPy

Appendix F - Introduction to NumPy

Other code examples and content are available on GitHub . The PDF and ebook versions of the book are available through Leanpub .

Node elevations and edge grades

Node elevations and edge grades

API usage limits: 50 requests per second, 2500 free requests per day, and 512 locations per request. So that's 2500 * 512 = 1.28 million total locations theoretically possible per day. But, the request URL is limited to 8192 characters, ...

Python Machine Learning - Code Examples

Python Machine Learning - Code Examples

https://github.com/rasbt/python-machine-learning-book

Introduction to Python

Introduction to Python

Open up a shell (e.g. git.exe , cmd.exe , or terminal.app )

UGC's 'preferred' journals are still predatory?

UGC's 'preferred' journals are still predatory?

The last list published was scattered across 5 scanned pdf documents. It was almost impossible to search. The Wire published an analysis of these Journals and found at least 35 of them Predatory

How many properties per building does each Barcelona neighborhood have, in percent?

How many properties per building does each Barcelona neighborhood have, in percent?

Read more about the data source here .

Drabbas kommuner som tar emot många flyktingar av ökad brottslighet?

Drabbas kommuner som tar emot många flyktingar av ökad brottslighet?

Under 2015 och 2016 tog svenska kommuner emot rekordmånga flyktingar från framför allt Syrien och Afghanistan. Det här borde, om teorin om sambandet mellan invandring och brottslighet, synas i statistiken. Vi borde se en uppgång i sexual- och våldsbrott i ...

Visualizing Caltrain Ridership - 2016 Weekday Average

Visualizing Caltrain Ridership - 2016 Weekday Average

Did you enjoy this post? Let me know on twitter . Also, Remix is hiring .

graph-based SLAMの例

graph-based SLAMの例

(c) 2017 Ryuichi Ueda

📑 Reflections. Deep Learning. Lesson 1

📑 Reflections. Deep Learning. Lesson 1

Improving the way neural networks learn: http://neuralnetworksanddeeplearning.com/chap3.html

📑 Reflections. Deep Learning. Lesson 2

📑 Reflections. Deep Learning. Lesson 2

Improving the way neural networks learn: http://neuralnetworksanddeeplearning.com/chap3.html

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Fair classifiers with adversarial networks

Fair classifiers with adversarial networks

We illustrate how one can use adversarial networks for building a classifier whose output is forced to be independent of some chosen attribute. We follow the adversarial networks setup described in "Learning to Pivot with Adversarial Networks" (Louppe, Kagan and ...

Elementary notions from game theory

Elementary notions from game theory

Here I am just going to show some of the most basic notions from game theory and Python code for the simplest of cases.

Python による「スクレイピング & 自然言語処理」入門

Python による「スクレイピング & 自然言語処理」入門

今回のセミナーでは初心者を対象にクローラーを作成し対象サイトのデータを収集、テキスト解析を行い、分析結果を得るまでの一連の流れについて、Python で使用するライブラリ、解析手法を交えて解説いたします。

This website does not host notebooks, it only renders notebooks available on other websites.

This website does not host notebooks, it only renders notebooks available on other websites.

Delivered by Fastly , Rendered by Rackspace

Monte Carlo Localization

Monte Carlo Localization

(c) 2017 Ryuichi Ueda