After running several statistical tests to assess my models, I decided to dig deeper into the theory and ask myself questions such as why the number of samples is relevant for the statistical test, why the standard deviation has a square root in the denominator, or why statisticians differentiate between Z- and t-distribution.
Since I did not find a blog post that answered all these questions, I decided to run some simulations in Python and post the results along with this article for people interested.
The central limit theorem states that if you sufficiently select random samples from a population…
This article is written for people who want to build a basic autoencoder using PyTorch. The dataset in which this article is based on is the Fashion-MNIST dataset.
The article is divided into the following sections:
As defined in Wikipedia:
An autoencoder is a type of neural network used to learn efficient data codings in an unsupervised manner.
In other words, the aim of an autoencoder is to learn a lower representation of a set of data, which is useful for feature…
This article is written for people who want to learn or review how to build a basic Convolutional Neural Network in Keras. The dataset in which this article is based is the Fashion-Mnist dataset.
Along with this article, we will explain how:
Fashion-MNIST is a dataset of Zalando’s article images — consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. We intend Fashion-MNIST…
This article is written for people who want to learn or review how to build a basic Convolutional Neural Network in Keras. The dataset in which this article is based on is the Fashion-Mnist dataset.
Along with this article, we will explain how:
Fashion-MNIST is a dataset of Zalando’s article images — consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. We intend…
This project has been developed within the research institution Cross Labs, which is located in Tokyo and focuses on pushing fundamental research towards a better understanding of the nature and artificial environments.
For this year’s ALIFE 2020 Conference held virtually from Montreal, we created an art piece to showcase our work in interactive storytelling, and the role agency plays within interactive interfaces. Our research focuses on manipulating, either enhancing, augmenting, deceiving, or controlling, an agent’s sense of agency.
Sense of agency can be defined as the feeling of control we have over our actions and the resulting consequences of those…
Machine learning tasks can be gathered into the four following categories:
During the last months, I’ve probably run the t-test dozens of times but recently I realized that I did not fully understand some concepts such as why it is not possible to accept the null hypothesis or where the numbers in the t-tables come from. After doing some research, I found that several articles provide those answers but not so many gather all of the information together.
Therefore, I decided to write this article to explain step-by-step the t-test so anyone can use it as a reference whenever they have to run the test or review the concepts.
In 2012, the IgNobel prize was awarded to an fMRI study of a dead salmon  since, after multiple testing over voxels, they found significant activity in the dead brain of a salmon.
This study is an example of what is known as Multiple Correction problem, defined in Wikipedia as “the problem that occurs when one considers a set of statistical inferences simultaneously or infers a subset of parameters selected based on the observed values ”. …
Acabo de cumplir tres años estudiando japonés y me he decidido a escribir este artículo sobre algunos consejos que me hubiese gustado escuchar a mí cuando empecé tres años atrás. Ojalá le sea de utilidad a alguien.
Importante: Parto de la base de que las personas que lean lo siguiente saben, por lo menos, Hiragana, Katakana y varias palabras en japonés. De no ser así, recomiendo dedicar al menos una semana a coger esa base.
Este artículo se centra en Vocabulary, Kanji and Listening. …
The term “normalization” usually refers to the terms standardization and scaling. While standardization typically aims to rescale the data to have a mean of 0 and a standard deviation of 1, scaling focuses on changing the range of the values of the dataset.
As mentioned in  and in many other articles, data-normalization is required when the features have different ranges. For example, normalizing when we have weight and height features is important as their range of values have different scales: e.g. [~45–130 Kg] for weight and [~120–230 cm] for height.
However, many articles do not mention other applications in…
Artificial Intelligence researcher and developer