Algoritmos de computación

LeelaFish UCI chess playing engine derived from Stockfish and LeelaChess Zero:  https://github.com/LeelaChessZero ,  https://github.com/official-stockfish/Stockfish Introduction This is a chess engine based in the Stockfish tree search but where we use the LCZero value head as evaluation function. So in this project we are just using the Stockfish code but replacing the human developed evaluation function for the neural network value head of the LeelaChess Zero project. This is a kind of experiment in which we try to figure out if the results are good even without the use of the MCTS LCZero does. Results Results are very promising and in a 1:1 ratio (when the number of nodes used by the original Stockfish or LCZero are forced to be equal to the number of nodes used by LeelaFish ) our development is able to beat both SF and LCZero. We used for these tests the LCZero network tesnet 10510. One thing is clear: the value head of the network is as good as the orig...

In this work, published in Science (Open Access version), we introduce the Generative Query Network (GQN), a framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes.  The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the agent's observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. (Google DeepMind) Como ya es costumbre, Google DeepMind acaba de dar otro paso (o pasito si peca uno de escéptico y quiere ser conservad...

Os dejo a continuación el contenido de un trabajo de investigation sobre machine learning que he realizado en mi escaso tiempo libre: https://github.com/Zeta36/random-memory-adaptation ------------------------------------------------------------------------------------------------------------------------------------------------------------------ Introduction. I present in this repository a (very simple) random memory adaptation model (RMA) inspired by the Google DeepMind paper: "Memory-based parameter adaptation (MbPA)" ( https://arxiv.org/pdf/1802.10542.pdf ) In the paper, point 4.1. CONTINUAL LEARNING: SEQUENTIAL DISTRIBUTIONAL SHIFT (inside experiments and results), they study the improvements their model suppose in relation to the catastrophic forgetting problem. They explored the effects of their model (MbPA) on continual learning, i.e. when dealing with the problem of sequentially learning multiple tasks without the ability to revisit a task. For this purposed they use...

About I explain how to export weights from a Keras model and import those weights in Keras.js, a JavaScript framework for running pre-trained neural networks in the browser. I show you later how to include the final result into a Phonegap Cordova mobile application. Introduction We are going to create a mushroom detector application for our mobiles. For this task we need to use a machine learning approximation, and as a good approximation we'll use the  KerasJS  framework. First Step: Build an image recognition system for several mushroom families. We need to begin training a Keras model in Python. For this purpose we'll use a transfer learning/fine tuning process over a pre-trained InceptionV3 model. The pipeline will be: Transfer learning: take a ConvNet that has been pre-trained on ImageNet, remove the last fully-connected layer, then treat the rest of the ConvNet as a feature extractor for the new dataset. Once you extract the features for all images, train a classifier f...

«¡Es la guerra! ¡Traed madera! ¡Más madera!»  (Los hermanos Marx) Introducción. El mundo de las ciencias de la computación están estos días de enhorabuena, un nievo hito histórico acaba de acontecer: hablamos por supuesto del casi milagroso desarrollo de Google DeepMind denominado AlphaZero , un modelo neuronal capaz de aprender de manera autónoma no supervisada (sin apoyo de datos etiquetados ofrecidos por el hombre) a jugar con capacidades sobrehumanas a varios juegos milenarios como el Go y el ajedrez ( aquí podéis descargar el paper de este proyecto). DeepMind acaba de demostrar así que la metodología que utilizaron para que un modelo neuronal aprendiera (con capacidades sobrehumanas) por sí misma sin apoyo de datos humanos el juego de Go, es generalizable a cualquier otro tipo de juego o situación. En el arriba comentado paper nos explican por ejemplo como en 4 horas (sí, sólo 4 horas), la red neuronal fue capaz de aprender a jugar al ajedrez (entre otros juegos) con una ca...

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0. If similar techniques can be applied to other structured problems, such as protein folding, reducing energy consumption or searching for revolutionary new materials, the resulting breakthroughs have the potential to positively impact society.  (Profesor David Silver) Hace unos meses   Google DeepMind   hizo público uno de sus resultados más asombrosos: una versión del modelo neuronal que fue capaz de derrotar al campeón del mundo de   Go , solo que esta vez no necesitaron hacer uso de ningún aprendizaje supervisado de juegos entre humanos (hablé en este mismo blog en   ...