How’s it going everyone, I decided to write a quick blog post to talk about a new service I’m working on. I’ve just finished university, and the job market is slow, so what better way to make money to feed the family than to release a specialised service? Enter (drumroll…) our new AI ChatBot Service for business owners. Here’s a demo of this in action (a quick video I made to showcase the service). Why is this such a good...Read more

Welcome to this post which will be the first in a series where I implement an end-to-end ML (Machine Learning) pipeline. To do this I will be using AWS (Amazon Web Services) and some of the tools on offer at Amazon i.e. SageMaker etc. This post aims to get you set up with an environment which you can then use to implement your own pipeline. The code for this project can be found in my GitHub (4igeek) repository. What are...Read more

Around a month ago, Apple released a report called “Introducing Apple’s On-Device and Server Foundation Models” which talks about how you can use “adaptors” to fine-tune a foundation large language model i.e. GPT-3 or Llama2 etc. In this post, (using the Apple research article) we will look at how we can use an external dataset to fine-tune one of these models using a technique called LoRA. Why would we want to do this? For a start, LLMs are trained on...Read more

I have just decided that I am going to embark on a journey to take the Google Data Analyst Certificate which is a program hosted on Coursera. The reason I made this decision was because I want to work in the field of machine learning and AI and the first step to doing that sort of thing well is being able to work (at an advanced level) with data. Having just completed my BSc (Hons) in Artificial Intelligence I am...Read more

This post is going to cover AI classification and give an introduction to decision trees (which will be covered in a future post). The idea is to give a good overall idea of what classification is in AI. The topics we are going to look at in this post are: Classification Algorithms Data Preparation Scikit-Learn Model Evaluation Overfitting & Underfitting Hyperparameters and Cross-Validation Metrics Decision Tree Introduction Classification is a supervised learning technique in that it is trained on an...Read more

Now we know how informed search works we can begin to look at how we can use it in different ways to satisfy the various criteria inherent in each of the problems that we face. For instance, in a modelling problem where we are trying to optimise the model based on the inputs and outputs, we are looking for the shortest route through something. If this is the case then the best method to use would be a method called...Read more

So far on this blog, we’ve spoken about and established what AI is and outlined a simple AI framework that we can develop further in the article titled “What is AI?” and we’ve also spoken about a specific type of problem that we could face in the real world which was an optimisation problem; we spoke about the kinds of search we can do based on both the type of search problem that we’re dealing with and the information that...Read more

If you would like to consider the basic AI framework in more detail before learning how we alter it to achieve different results based on the various criteria inherent in the problem we’re dealing with then it would be a good idea to read the post titled “Exploring the Basic AI Framework in More Detail” before reading this post. A good way to understand how a computer solves a problem is to simply consider how a human would solve it....Read more