Reinforcement learning is an area in machine learning which is focused mainly on training an agent in a given environment in order to get the maximum reward based on the action it can take at the moment.
One team of the University of Oxford to create a better performance of a AI in Atari videogames. They have inspired with the demostration of combine Q-learning with deep learning to play Atari games maked in the work of Mnih et al (2013).
It’s common to hear about detection of emotions in pictures of people faces, but other area that can be usefull to now the emotions of people with only analysing what they write in places like comments in Facebook or Twiter. This open a new possibility to automatize the analisys of…
In 2016 researchers published the paper Image Style Transfer Using Convolutional Neural Networks in which they presented a technique that enables a Neural Network to transfer a style from an artwork onto a photograph. This technique became popular and it is now available in apps…
Big data has been the new tendency in many areas of study, including medicine. The three major steps of actually using all of the data provided by patients are:
This is based on Quartz’s article “Machine learning is being used to uncover the mass graves of Mexico’s missing”. If you want to know more click on the link.
Using Reinforcement Learning (Learning to take better actions in order to have a cumulative reward), scientifics of DeepMind Technologies developed a deep learning model for learning control policies directly from high-dimensional sensory input applied to learning and playing different gamees form…
As a part of the Google’s “A.I. Experiments” (https://aiexperiments.withgoogle.com/) this project was developed in conjuction with the Cornell Lab of Ornithology. The main purpose of this was to create an AI for classifying and visualizating the…
When someone mentions StarCraft, its almost granted that 90% of the people hearing imagines a korean guy that has played for 47 hours nonstop, no sleep, no food, and most likely no bathroom. I will not deny that koreans are the epitome of StarCraft players, but ever since 2011…
This post explores the use of DBN for image reconstruction and defect detection.
Give emotions to a system like the artifitial neuron networks is one approach in ordder to create a better model of a biological brain. The emotions are a set of biological and biochemical reactions, the ones more associated to the emotions are the hormones. They can, in sort way, modulate the decisions…
MYO is an armband that is used to detect electric pulses from your arm which can later be used to detect a certain movement. These electric pulses are detected by 8 different sensors in the armband which go around your arm. Before MYO only released a version of the armband which detected predefined…
A thought that often crawls the mind of someone interested in videogame development is why the hell machine learning is not yet a standard in the godamn industry?Artificial inteligence is often critized when the enemy stands, slowly dying, while…
This is based on Quartz’s article “Netflix’s new AI tweaks each scene individually to make video look good even on slow internet”. If you want to know more click on the link.
Para este café académico, me di a la tarea de encontrar alguna aplicación interesante en área de procesamiento de imágenes con redes neuronales. Encontre una aplicación bastante atractiva donde se retoman algunos conceptos que hemos estado viendo en…
Hace unas pocas horas, tuvo lugar el Google Cloud Next ’17 donde, entre otras cosas, se presentó una API para distinguir objetos (verbos y sujetos) en los videos.
(Trabajo por parte de la Universidad de Princeton) … Para la automatización del proceso de conducción, existen 2 paradigmas previamente establecidos que son:
En esta ocasión, se presenta el primer paso que se realizó para resolver el problema de la conversión de imágenes de señas del lenguaje de señas mexicano a sus respectivas letras del alfabeto, con la excepción de las letras J…
Durante el semestre pasado trabajamos en un reconocedor de señas del lenguaje de sordos y logramos hacer que reconociera entre 6 distintas letras. Yo me dedique al área del pre procesamiento de imágenes, mi trabajo era tomar imágenes…
El procesamiento de imágenes es una herramienta ampliamente utilizada en muchas áreas, como la Visión Artificial. Consiste en procesar señales, la mayoría de veces digitales, aunque también pueden ser analógicas u ópticas (captación de luz), y realizar con ellas operaciones para…
El método Monte Carlo es otro método estocástico (ver Cadenas de Markov) que utiliza una serie de algoritmos para realizar simulaciones aleatoriamente, esto permite asignarle valores aleatorios a un conjunto A de variables independientes, para que el conjunto B de variables dependientes tome…
La realidad para los seres humanos consta de 3 dimensiones espaciales, sin embargo nuestros ojos como las cámaras o sensores con las que las computadoras pueden tomar perspectiva del mundo real solo pueden recibir imágenes en 2 dimensiones. El ser humano al contar con visión binocular y un…
