Entradas

Mostrando entradas de agosto, 2017

Deep neural networks visualization

Imagen
In this publication I present a "toy tool" to see how neurons on a Deep Neural Network (DNN) modify the links between them. These links are also called Weights. For those with technical knowledge, the "bias" unit is not shown (Because of lack of time, I will upgrade it later). In addition I haven't implemented yet the predict option, I would probably add it later. Technical Notes: This DNN uses standard back propagation without optimizations such as Adam optimizer or regularization parameters.   I am using Math.js  for the matrix operations. There are some errors I haven't figured out yet how to solve them, specially for Nan values that will appear when showing the visualization (Sometimes happens, no worry =) ) The last layer, the output layer is a sigmoid layer by default. Maybe later I will implement a linear function for regression analysis. And it has been implemented for binary classification by the moment. The weights are randomly init...

Google charts timeline online for non software developers

Imagen
In this post I provide an online way to create a Google Chart timeline type. Google charts are for software developers or people with some coding skills. Here, I try to allow common citizens use this technology. After reading the instructions you will be able to create a chart like the following: There are two ways Way I: Write in the input text field below The format write in it is: Category name1, event name1,Start date1, End Date1; Category name2, event name2,Start date2, End Date2; ...Category nameN, event nameN,Start dateN, End DateN Category name is the row name where the event will be added. According to the example above, it would be "President" or "Vice President". Event name is the event in colors that will be added to the categories. An event name would be "George Washington". Start date and end Date are the start and end date/time of the event. Both have the following structure "yyyy/mm/dd hh:mm" . It...

Google Chart Word tree for non programmers online

Imagen
In this series of publications I am aiming to enable Google charts to people without programming skills. Maybe you need a fancier way to present your charts than what your current office applications provide you. Or for any other case, here I present an option to extend your possibilities. In this case, you would be able to have a tree graphic with the following structure: I have seen this kind of graphic in taxonomy reports. Therefore, I have used some  International Committee on Taxonomy of Viruses (ICTV) data as input example. Two ways to get a similar chart: Way 1 In the text box below insert sentences separated by a ";". The root word will be the first word that appears in this field. For example, a sentence like "bryan is great;bryan is awesome;bryan the best", will produce the following diagram: Remember not adding a ";" at the end of all the text. Add ";" only between sentences. Steps: Write the sente...

Google Chart Sankey Diagram online for non software developers

Imagen
I saw lots of tutorials of how to create a Sankey diagram but I couldn't find a quick way to see my data without installing or configuring parameters. Thus, here I present a Sankey Diagram to visualize your data. In case you are a software developer this may result to be something simple for you, but in case you don't have programming skills but want a Sankey diagram, this post is for you. You have to upload a CSV file, comma separated in the format: NodeA, NodeB, Weight An example of a CSV file could be: Root A,Branch X,3 Root B,Branch X,8 Root B,Branch Y,2 Root B,Branch Z,3 Branch X,End 1,19 Branch X,End 2,2 Branch X,End 3,4 Branch Y,End 1,10 Branch Y,End 4,17 Root B,Branch ZX,4 Branch ZX,End 1,1 This will create the following Graph: Instructions of use: Way one Click on Chose File and search for your CSV file. In the text field you will see your data loaded. You should see "NodeX1,NodeY1,N1;NodeX2,NodeY2,N2... Click in the button Process ...