Working Memory Workout

  •        37

Working Memory Workout is a working memory training game based on the N-back, a task researchers say may improve fluid intelligence. It greatly expands on the N-back, with dynamic difficulty adjustment, 13 game modes, 61 stimuli, 4 time modes, and a difficulty-ratcheting helper.



Related Projects


A brain training program based on scientific, peer reviewed research. This is NOT a game like Brain Age or Big Brain Academy. It's a workout and users report feeling exhausted after using it. The program focuses on "exercising" the neural pathways from hearing to memory in or...

Brain Workshop

Brain Workshop is a Python implementation of the Dual N-Back mental exercise. This exercise is the only mental activity that has been scientifically shown to improve your short-term memory (working memory) and fluid intelligence.


iMemory is the computer-version of the well-known brain training game with a couple of special features, different from the \\\quot;hardware\\\quot; card version. Create your own memory games with those pictures you like, e.g. take the pictures of your la


gbrainy is a brain teaser game and trainer to have fun and to keep your brain trained. gbrainy's project page: There is also an on-line version:

brain - [UNMAINTAINED] Simple feed-forward neural network in JavaScript

Download the latest brain.js. Training is computationally expensive, so you should try to train the network offline (or on a Worker) and use the toFunction() or toJSON() options to plug the pre-trained network in to your website. Use train() to train the network with an array of training data. The network has to be trained with all the data in bulk in one call to train(). The more training patterns, the longer it will probably take to train, but the better the network will be at classifiying new patterns.

neuraltalk2 - Efficient Image Captioning code in Torch, runs on GPU

Update (September 22, 2016): The Google Brain team has released the image captioning model of Vinyals et al. (2015). The core model is very similar to NeuralTalk2 (a CNN followed by RNN), but the Google release should work significantly better as a result of better CNN, some tricks, and more careful engineering. Find it under im2txt repo in tensorflow. I'll leave this code base up for educational purposes and as a Torch implementation. Recurrent Neural Network captions your images. Now much faster and better than the original NeuralTalk. Compared to the original NeuralTalk this implementation is batched, uses Torch, runs on a GPU, and supports CNN finetuning. All of these together result in quite a large increase in training speed for the Language Model (~100x), but overall not as much because we also have to forward a VGGNet. However, overall very good models can be trained in 2-3 days, and they show a much better performance.


RTanque is a game for (Ruby) programmers. Players program the brain of a tank and then send their tank+brain into battle against other tanks.

Math Trainer

Math Trainer trains your brain by creating easy calculus problems in variable difficultly for you. this projects also contains various other tools related to mathematical topics.

mms - Modern Memory Safety in C/C++

This repo contains the slides for a training course originally developed in 2012. It has been delivered to many students since its creation. It's sold out at the Black Hat USA conference several years in a row. The content has gone through many iterations based on feedback from those classes. The original training focused mainly on browser vulnerability discovery and exploitation. This latest version still focuses on that but also covers more topics such as custom memory allocators, hardening concepts, and exploitation at a high level. This training would not have been possible without open source projects to study, or freely available texts from the security community. In fact, the security community is one of the best proponents of open source. I want to help continue that trend.

ForNix - For *Nix Users

ForNix is a documentation and help page with tips and tricks for users and developers. It will be devoted to Linux and other *NIX. P.S.: quot;fornixquot; is also an important brain structure involved on learning and memory.


With this Python module (based on C++ code) it is possible to create a Brain Comp. Interface (BCI) and herewith to get EEG data online and evaluate the data while receiving it. - Up to now, this tool relies on the Brain Vision Rec. as EEG software -


kzenchat is small handy brain-tool for chatting with yourself. It seems to be a bit schizophrenic software on first glance, but in real it's a powerful brain-tool for exploring yourself and solving problems. It uses QT and some of KDE libraries for it's G


Brain imaging software produced by the Brain Research Imaging Centre of The University of Edinburgh.

Brain Relax

Brain Relax is a translator from the BF (BrainF**k) programming language (a Turing-complete language) to other programming languages (such as C, TCL, PHP, Pascal, Perl, Basic, Python, etc.)

Brain Network Search Engine

Brain Net. A Distributed Search Engine Network. Aims to be a scalable distributed search engine allowing dynamic connection of nodes. Performance depends on bandwidth.


Brain is a prototype-based, object-oriented scripting language. It is something between Scheme, Smalltalk and JavaScript.

MXNet - A Deep Learning Framework

MXNet is an open-source deep learning framework that allows you to define, train, and deploy deep neural networks on a wide array of devices, from cloud infrastructure to mobile devices. It is highly scalable, allowing for fast model training, and supports a flexible programming model and multiple languages. MXNet allows you to mix symbolic and imperative programming flavors to maximize both efficiency and productivity.

tensorflow - Computation using data flow graphs for scalable machine learning

TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) that flow between them. This flexible architecture lets you deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device without rewriting code. TensorFlow was originally developed by researchers and engineers working on the Google Brain team within

CNTK - Computational Network Toolkit (CNTK)

The Microsoft Cognitive Toolkit is a free, easy-to-use, open-source, commercial-grade toolkit that trains deep learning algorithms to learn like the human brain. It is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph.

Zyan Drench, a game for Android

Zyan Drench is a simple yet very entertaining game for Android phones developed using Zyan Communication Framework: