This is the last of the series of articles about this project, if you haven’t read the previous rounds yet, I recommed you to check them out. If you already read them thank you very much for your interest and let’s get started!
The last weeks was a very stressful one, I tried to train the model using different methods (changing the reward function many times, normalyzing the inputs, reshaping the NN, etc) but unfortunatelly I couldn’t make it work 😕, the model has a behavior pretty silly and it doesn’t seems to converge.
So I decided to stop the…
This week I was researching a lot the implementation of a reinforcement learning algorithm to train the agent for the game. So after reading some articles, forums and documentation, I confirmed that what I need to implement is Deep Q learning algorithm.
Based on this article called Playing Atari with Deep Reinforcement Learning, the algorithm looks like the following:
If you haven’t read the round 1article yet, I recommend you check it out before you start reading this article. If you already read round one, let’s get started.
This is a starting point of a series about an adventure I want to share. This article explores an idea that came to my mind the last week and that I’m researching about. The idea is to create an expert AI player of Mortal Kombat based on reinforcement learning techniques.
Note: On this series of articles I will carry out some research about something that, in my own view, it could work. So if you came here searching for answers, this is the wrong place, here we will find questions, many of them.
The power of deep learning architectures and the handy Tensorflow.js library allows us to create interesting applications that change the way we interact with computers. In this case, we use a pose estimation neural network to create a virtual steering wheel based on the position of the wrists.
In this project I will show an example of integration between web applications and deep learning models to transfer the application controls from the mouse and keyboard to the human body.
In this case, I created a virtual steering wheel to drive a vehicle on a highway.
The growth of processing power in devices and Machine learning allows us to create new solutions that a few years ago couldn’t have been achieved. In this case, I want to show an interesting way to perform authentication using Flutter and Tensorflow Lite with face recognition.
I will explain step by step, how is the process of building a fairly simple facial recognition app that contains 3 functionalities: Sign Up, Sign In and Clear DB.
In recent years, the interaction in Twitter has become increasingly toxic with the rise of hate speech, harassment and offensive content. In this article, I want to explain how to build a simple toxic tweet detector, using twitter API and tensorflow.js.
In this post I want to show step by step how to build a web application that shows the last toxic tweets and retweets from the given user.
The application will receive 2 parameters: tweets to search and username.
Edge devices, such as smartphones, have become more powerful with the passing of time and enabled an increasing number of on-device machine learning use cases.
TensorFlow is a platform for building and training neural networks, which allow detecting and deciphering patterns and correlations, analogous to the learning and reasoning used by humans.
TensorFlow’s flexible architecture enables developers to deploy computation to one or more CPUs or GPUs on desktops, servers, or mobile devices with a single API. …
Cascading Style Sheets, better known by its acronym CSS, is a language used to display the design elements of a web page, which generally must be defined separately.
HTML and XML documents contain information only about the content or semantics of some of the components of a website, while design resources are found separately in so-called CSS files. If Stylesheets are used, the server has to access them (where multimedia content such as photos, videos, etc. is stored) each time the web is visited, which clearly has an impact on load times. The larger and more complex the CSS files…
This article shows you step-by-step how to set up and run your own customized video player in Flutter to play videos from the device file-system or using a given URL such as http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/BigBuckBunny.mp4.
Once you do that, you need to run flutter packages get.
Be sure that the following line appears in the
<application ...> tag located in
Also make sure the line below appears outside the
<application ...> tag: