1. Overview

Source: https://www.robots.ox.ac.uk/~vgg/data/pets/

1. Overview

An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”. Along with the reduction side, a reconstructing side is learned, where the autoencoder tries to generate from the reduced encoding a representation as close as possible to its original input, hence its name.

What make people become good game players? They get the game instruction, start practicing and then learn from failure. How about a computer? Can we train it to play a game? The answer is absolutely! And the process of teaching or training the computer to play game is super interesting. This post is written to guide you, step by step, to create your own Game AI that is able to learn to play this game without any hardcoded rules.

Hey tech enthusiasts!

Ever thought of a year-end company trip as a system reboot? That's exactly what my getaway to Ho Coc - Ho Tram in Ba Ria - Vung Tau felt like – a perfect blend of team spirit and sea breeze.

The Epic Year-End Logout:

Our journey began not with code pushes but with packed bags, as nearly 100 of us, myself and my family included, set off for a year-end company trip. It was time to exchange our usual digital tools for some real-world team building and family bonding.