An Introduction to Implementing Neural Networks using TensorFlow
Posted by Armando Brito Mendes | Filed under materiais ensino, software
Uma boa introdução ao tensor flow e deep learning
Introduction
If you have been following Data Science / Machine Learning, you just can’t miss the buzz around Deep Learning and Neural Networks. Organizations are looking for people with Deep Learning skills wherever they can. From running competitions to open sourcing projects and paying big bonuses, people are trying every possible thing to tap into this limited pool of talent. Self driving engineers are being hunted by the big guns in automobile industry, as the industry stands on the brink of biggest disruption it faced in last few decades!
If you are excited by the prospects deep learning has to offer, but have not started your journey yet – I am here to enable it. Starting with this article, I will write a series of articles on deep learning covering the popular Deep Learning libraries and their hands-on implementation.
In this article, I will introduce TensorFlow to you. After reading this article you will be able to understand application of neural networks and use TensorFlow to solve a real life problem. This article will require you to know the basics of neural networks and have familiarity with programming. Although the code in this article is in python, I have focused on the concepts and stayed as language-agnostic as possible.
Let’s get started!
Table of Contents
- When to apply neural nets?
- General way to solve problems with Neural Networks
- Understanding Image data and popular libraries to solve it
- What is TensorFlow?
- A typical “flow” of TensorFlow
- Implementing MLP in TensorFlow
- Limitations of TensorFlow
- TensorFlow vs. other libraries
- Where to go from here?
Tags: big data, data mining, machine learning, text mining
Controlling for test variables
Posted by Armando Brito Mendes | Filed under estatística, lições, materiais ensino, software
alguns apontamentos sobre testes com vars de controlo
3.2 Three (or more) variables
Introducing a third variable. Controlling for test variables. Elaboration.
Logical model is X → Y . T (the effect of X on Y controlling for T) where:
Y = Dependent variable
X = Independent variable
T = Test variable(s)
3.2.1 Elaboration
Tags: inferência, software estatístico
What is SPSS?
Posted by Armando Brito Mendes | Filed under estatística, materiais ensino, software
Uma explicação para as ciências sociais
What is SPSS and what does it do?
SPSS consists of an integrated series of computer programs which enable the user to read data from questionnaire surveys and other sources (e.g. medical and administrative records) to manipulate them in various ways and to produce a wide range of statistical analyses and reports, together with documentation.
Most users will have access to SPSS via their college or workplace or by purchasing the Gradpack version (specially priced for students). Full details are on IBM SPSS Solutions for Education and there is a comparison table showing what is available in each version.
Tags: IBM SPSS Statistics, software estatístico
Summary guide to SPSS tutorials
Posted by Armando Brito Mendes | Filed under data sets, estatística, materiais ensino, software
Bom site com vários recursos sobre a utilização do IBM SPSS
Catalogue of SPSS tutorials is an Excel *.xlms file containing a full listing (with hyperlinks) of all tutorial files.[may not be completely up-to-date]
Guide to pop-out menus shows all the screenshots for menus and sub-menus for Survey Analysis Workshop [may not be completely up-to-date and site has been re-organised, so needs a re-write, but still useful to show you what to expect]
There are more than 600 pages of downloadable tutorials arranged in four blocks.
Block 1: From questionnaire to SPSS saved file
1.1: The language of survey analysis
1.2: How do data relate to questionnaires?
1.3: Reading raw data into SPSS
1.4: Completing your data dictionary
1.5: Utilities [still in preparation]
Block 2: Analysing one variable
2.1: Nominal and ordinal variables
2.2: Interval scale variables
2.3: Data transformations
Block 3: Analysing two variables (and sometimes three)
3.1 Contingency tables
3.2 Three variables
3.3 Multiple response
3.4 Comparing means
3.5: Conditional transformations
Block 4: Hypothesis testing
[Still in preparation: provisional contents listed below: page also has links to some useful resources for statistical concepts]
Hypothesis testing
4.2a t-test and one way anova
4.2b Testing differences between three or more means
4.3 Chi-square (has one tutorial)
4.4 Regression and correlation
4.5 Association, structure and cause
SPSS files and documentation used for tutorials and exercises
Tags: análise de dados, IBM SPSS Statistics, inquéritos, software estatístico
SPSS videos e trials
Posted by Armando Brito Mendes | Filed under estatística, software
Um site da IBM com bastantes recursos sobre o SPSS
Software Trial: IBM SPSS Statistics Desktop
Start leveraging your data today to identify your best customers, forecast future trends, improve supplier performance, and more.
![Software Trial: IBM SPSS Text Analytics for Surveys Trial Software [US]](http://www.ibm.com/software/analytics/spss/products/statistics/images/icon-text-analysis-60x60.jpg)
Software Trial: IBM SPSS Text Analytics for Surveys Trial Software [US]
IBM SPSS Text Analytics for Surveys uses powerful natural language processing technologies specifically designed for survey text.
![Software Trial: IBM SPSS Amos Trial](http:///www.ibm.com/software/analytics/spss/products/statistics/images/icon-amos-60x60.jpg)
Software Trial: IBM SPSS Amos Trial
IBM SPSS Amos gives you the power to easily perform structural equation modeling (SEM).
![Online Demo: IBM SPSS Regression in action](http://www.ibm.com/software/analytics/images/offers/video-thumb/od_spssrc_ibm_spss_regression_127x96.jpg)
Online Demo: IBM SPSS Regression in action
Watch how powerful regression techniques can help you discover hidden relationships in your data.
![Online Demo: Two-step cluster analysis: Find natural groups in your data [US]](http://www.ibm.com/software/analytics/images/offers/video-thumb/od_spssrc_ibm_spss_statistics_base_127x96.jpg)
Online Demo: Two-step cluster analysis: Find natural groups in your data [US]
Watch a short demonstration of the two-step cluster analysis technique in SPSS Statistics Base.
![Online Demo: Online Demo: Statistical analysis with confidence using IBM SPSS Statistics [US]](http://www.ibm.com/software/analytics/images/offers/video-thumb/od_spssrc_ibm_spss_statistics_product_overview_127x96.jpg)
Online Demo: Online Demo: Statistical analysis with confidence using IBM SPSS Statistics [US]
Explore the power of statistical analysis in your organization IBM Analytics IBM Analytics
![White Paper: White Paper: Better decision making under uncertain conditions [US]](http://www.ibm.com/software/analytics/images/thumbs/offers/wp_spssrc_simulation_modeling_in_ibm_spss_statistics_98x120.jpg)
White Paper: White Paper: Better decision making under uncertain conditions [US]
This paper describes Monte Carlo simulation, the value of this technique for risk analysis and how SPSS Statistics and its Monte Carlo simulation capabilities can help businesses assess for risk.
![White Paper: The Risk of Using Spreadsheets for Statistical Analysis [US]](http://www.ibm.com/software/analytics/elq/images/thumbs/IMW14297USEN.jpg)
White Paper: The Risk of Using Spreadsheets for Statistical Analysis [US]
Despite their popularity, spreadsheets may not be well suited for analysis and decision making. This paper explores why, and describes a better alternative.
Tags: análise de dados, IBM SPSS Statistics, software estatístico
Site oficial IBM SPSS
Posted by Armando Brito Mendes | Filed under estatística, software
site com muita info. e documentação para o SPSS
What is IBM SPSS?
What if you could get deeper, more meaningful insights from your data and predict what is likely to happen next? IBM SPSS predictive analytics software offers advanced techniques in an easy-to-use package to help you find new opportunities, improve efficiency and minimize risk.
![spss reporting icon](https://www.ibm.com/analytics/us/en/technology/spss/images/spss_featureicon1.png)
Statistical analysis and reporting
Address the entire analytical process: planning, data collection, analysis, reporting, and deployment.
![spss predictive icon](https://www.ibm.com/analytics/us/en/technology/spss/images/spss_featureicon2.png)
Predictive modeling and data mining
Use powerful model-building, evaluation, and automation capabilities.
![spss dsm icon](https://www.ibm.com/analytics/us/en/technology/spss/images/spss_featureicon4.png)
Decision management and deployment
Activate your analytics with advanced model management and analytic decision management on prem, on cloud or as hybrid.
![spss big data icon](https://www.ibm.com/analytics/us/en/technology/spss/images/spss_featureicon3.png)
Big data analytics
Analyze big data to gain predictive insights and build effective business strategies.
Tags: data mining, IBM SPSS Statistics
curso de KNIME
Posted by Armando Brito Mendes | Filed under mapas SIG's, materiais para profissionais, software, videos, visualização
Muito bom curso de KNIME, é introdutório mas introduz um grande número de funcionalidades.
KNIME Online Self-Training
Welcome to the KNIME Self-training course. The focus of this document is to get you started with KNIME as quickly as possible and guide you through essential steps of advanced analytics with KNIME. Optional and very useful topics such as reporting, KNIME Server and database handling are also included to give you an idea of what else is possible with KNIME.
- Installing KNIME Analytics Platform and Extensions
- Data Import / Export and Database / Big Data
- ETL
- Visualization
- Advanced Analytics
- Reporting
- KNIME Server
Tags: análise de dados, big data, data mining, Knime, text mining
Tinker With a Neural Network
Posted by Armando Brito Mendes | Filed under software, visualização
Uma excelente aplicação web para perceber como as redes neuronais funcionam
Um, What Is a Neural Network?
It’s a technique for building a computer program that learns from data. It is based very loosely on how we think the human brain works. First, a collection of software “neurons” are created and connected together, allowing them to send messages to each other. Next, the network is asked to solve a problem, which it attempts to do over and over, each time strengthening the connections that lead to success and diminishing those that lead to failure. For a more detailed introduction to neural networks, Michael Nielsen’s Neural Networks and Deep Learning is a good place to start. For a more technical overview, try Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
This Is Cool, Can I Repurpose It?
Please do! We’ve open sourced it on GitHub with the hope that it can make neural networks a little more accessible and easier to learn. You’re free to use it in any way that follows our Apache License. And if you have any suggestions for additions or changes, please let us know.
We’ve also provided some controls below to enable you tailor the playground to a specific topic or lesson. Just choose which features you’d like to be visible below then save this link, or refresh the page.
What Do All the Colors Mean?
Orange and blue are used throughout the visualization in slightly different ways, but in general orange shows negative values while blue shows positive values.
The data points (represented by small circles) are initially colored orange or blue, which correspond to positive one and negative one.
In the hidden layers, the lines are colored by the weights of the connections between neurons. Blue shows a positive weight, which means the network is using that output of the neuron as given. An orange line shows that the network is assiging a negative weight.
In the output layer, the dots are colored orange or blue depending on their original values. The background color shows what the network is predicting for a particular area. The intensity of the color shows how confident that prediction is.
What Library Are You Using?
We wrote a tiny neural network library that meets the demands of this educational visualization. For real-world applications, consider the TensorFlow library.
Credits
This was created by Daniel Smilkov and Shan Carter. This is a continuation of many people’s previous work — most notably Andrej Karpathy’s convnet.js demo and Chris Olah’s articles about neural networks. Many thanks also to D. Sculley for help with the original idea and to Fernanda Viégas and Martin Wattenberg and the rest of the Big Picture and Google Brain teams for feedback and guidance.
Tags: data mining, machine learning, web apps
How to create a slicer in Excel
Posted by Armando Brito Mendes | Filed under lições, materiais ensino, materiais para profissionais, software
Bom tutorial de como usar umas das novas funcionalidades do Excel
For dashboards and quick filtering, you can’t beat Excel slicers. They’re easy to implement and even easier to use. Here are the basics–plus a few power tips.
Tags: Excel
MySQL Documentation
Posted by Armando Brito Mendes | Filed under linguagens de programação, materiais para profissionais, software
Montes de documentação sobre todos os produtos MySQL
Guardar
Tags: SQL