In continuation to Part 1 of “Creating a Machine Learning Auto-shoot bot for CS:GO.” in this short series of articles, I demonstrate how a modified version of the VGG network originally designed by the Visual Geometry Group at Oxford University performed in the task of real-time training to detect targets in the First-Person Shooter game Counter-Strike Global Offensive.

I originally chose the VGG network because of its simplicity, when I first chomped into the subject of Neural Networks in early 2020 I started at AlexNet, although it follows the same principle of a CNN, AlexNet was designed specifically to get the best performance out of a specific dual GPU setup in the year of 2012. Because this project aims its sights at the task of real-time training I knew that my CNN implementation would have to be very light weight, which meant that deriving my architecture from one such as VGG would be the best scenario to proceed. I liked that the amount of filters per layer in VGG incremented to the power of two and that VGG only used 3x3 filters to power of two depth. Although the series of VGG networks were designed for multi-classification my task was one of binary classification (shoot or don’t shoot) and that’s where I realised that additionally to reducing the number of layers and filters in the VGG network I could further simplify by completely removing the fully connected layer for a Global Average Pooling (GAP) layer essentially transitioning from a Convolutional Neural Network (CNN) to a Fully Convolutional Network (FCN). …

In what is a continuation of my original article on “Training a Neural Network to Autoshoot in FPS Games.” in this short series of articles I will be exploring the application of Machine Learning (ML) and Artificial Neural Networks (ANN) to implement an Artificial Intelligence (AI) which is able to use real-time training to create a model which can identify targets in, although not limited to, Valve Software’s game of Counter-Strike Global Offensive.

The first port of call for this series was to do a quick implementation using the resources I already had available to me, and in this case that was TFCNNv2, a simple yet feature-rich C library I had been working on which implements classical Feed-Forward Neural Networks. …

From a young age, I discovered the importance of getting a head start in life, I remember around the age of 10 saying to my parents “I want to be a race car driver” and them telling me that this was highly unlikely, when I asked why they told me “the drivers you see on TV probably started at a young age” and naively I said “well why can’t I start at a young age, we could get lessons at the local go-karting centre” they told me “we don’t have the money for you to do go-karting lessons”.

It was a typical desire of a young boy and it was probably one of the few times my parents didn’t lie to me in order to make their lives easier, but I now realised that if I was going to make something of my life I had to get a head start on everyone else. …

This is a brief and partly mundane account of how the Huawei AspiegelBot (PetalBot) web crawler discovered and exploited a serious vulnerability in the back-end services of a website I operate. What started as a simple security vulnerability found by a web-crawler quickly escalated into a world-wide attack from hordes of faceless wanna-be hackers and script kiddies running run-of-the-mill exploit and directory scanning software.

It all started when I noticed what seemed to be some kind of Denial-of-Service (DoS) attack against the server I use to host the VF Cash website and services. These attacks were particularly odd because I noticed that not only did the attacks exhaust the bandwidth of the server but also, they locked up the server in question requiring that the server was restarted to regain any kind of operation or remote access. I thought it strange, busy with other tasks I just rebooted the server, but the problem persisted for about three days at a frequency of 1/2 times per day before I came to realise what exactly the problem was.. …

On the 23rd of April 2019, I set out to create a Digital Currency, inspired by the insurgence of other alternative currencies to Bitcoin but also unlike any other digital currency designed to date, it broke all the conventional norms; allowing instant transactions with no fees in a decentralised manner without a regular consensus model.

Around this time everyone was talking about micro-transactions and for once the Proof-of-Stake (PoS) model of consensus was becoming the popular option, even though for years prior it was rejected for having been no less centralised than any other traditional institution.

I was never a fan of PoS and still, to this day, it’s not an option I would personally be satisfied with. This is because I do not believe in a decentralised system that allocates more power to particular nodes or individuals — even if this was voted upon by the majority of network participants. I truly believe that in any fair decentralised network that everyone should have the same rights, power, stake, or influence, in the overall network and its operations. Regardless of how much value you hold in that network in currency or any other medium. …

I had been working in the advertising industry, specifically in programmatic advertising, since 2013; and exited in November of 2019, my total period of operation was 6 years, and five of those years had been spent as a developer where I built programmatic advertising platforms for other clients, usually under contract, Supply-Side and Demand-Side. This article consists mostly of my experiences in my final year when I decided to give a shot at running my own Demand-Side Platform after 5 years of making them for other people. I don’t regret my time working with OpenRTB; it was interesting, and although my DSP made a small amount of profit I was happy to have made a profit at all. …

When it comes to rendering 3D content on the web there are quite a few options, the most popular being Three.js or the lesser-known p5.js. The problem being is that both of these are JavaScript frameworks, and when working with 3D usually you want the performance and portability of C, which in all respects is very similar to JavaScript being almost identical in syntax.

Web browsers support two types of OpenGL as stated on the official Wikipedia page; WebGL 1.0 which is based on OpenGL ES 2.0 and WebGL 2.0 which is based on OpenGL ES 3.0.

Generally if you desire to go for maximum compatibility you will go with the lesser of the two. In which case you will be working with GLSL ES 1.0 for your shader programs. …

In this article, I will ultimately show you how to make an Autoshoot bot for any FPS game using a simple neural network on Windows or Linux.

It all started in early 2020, I was getting a bit bored with my usual routine — think of a game idea — execute a game idea. I’d been making terrible indie games for years, one of which did ‘make it big’ but in the hands of a big studio, however alone, I always lacked the artistic prowess to make something truly compelling.

My brother mentioned to me how Artificial Intelligence was playing a major role in the automation of jobs in the company he was working for and so with nothing else to invigorate me I decided to give my hand at Neural Networks. …