This past two weeks now have been specifically interesting in understanding how fast.ai sees images since imaging and image processing have been a significant part of my history. I have some questions about why grey scale and RGB were chosen as standards for working with images, my guess is that these were the simplest forms of digitizing the image data. …


How do you write an article that people read, like and comment it, this is a question that has plagued me for some time, why do some articles get over 1000 views while others get less than 10?

Here are some tips from the lessons and experiences over time, making people know, like and follow you takes time and effort.

A thousand plus views …???

There isn’t a simple answer to that question, the answer is that there are many factors that play a roll in making your articles popular, the single biggest factor in getting views, likes and comments…


Supervised Machine Learning

Definition:

A definition of Supervised Machine Learning is machine learning that has human help or supervision in the learning process.

Explanation

The human help is by sorting and labelling the data that is fed to the computer, in other words making sure that the computer receives and uses clean data and it does not need to figure out what the data is.

For example, if you are going to use pictures you would label the picture with the description of what the picture is about and this could be as simple as “dog” or “cat”. …


Introduction

A simple definition of a Language Model is an AI model that has been trained to predict the next word or words in a text based on the preceding words,
its part of the technology that predicts the next word you want to type on
your mobile phone allowing you to complete the message faster.

The task of predicting the next word/s is referred to as self-supervised learning, it does not need labels it just needs lots of text.

The process applies its own labels to the text.

A language mode can mono linguistic or poly linguistic. Wikipedia suggests that…


Extrapolation — Useful tool or dangerous data

Useful tool or dangerous data

One cannot talk about extrapolation without referring to regression, in fact regression is an integral part of extrapolation. A simple explanation of regression used for extrapolation is finding the best fit mathematical relationship between the dependent and independent variables in a data set where the dependent variables are continuous.

Extrapolation uses the relationship determined by the regression to predict dependent and independent values that are outside of the data set used for training.

Understanding different types of data sets and where extrapolation can be applied:

A simple explanation of different types of data sets and uses for deep learning modes…


Regression — a short introduction of the method used in fast AI

What is regression?

Regression is finding the relationship between the dependent and independent variables and different methods of calculating regression are used in AI for different reasons such as predictive behavior, finding the midpoint of a face in images, finding the size and position of a circle in a square, etc.

REGRESSION techniques are widely employed to solve tasks where the goal is to predict continuous values. …


Is there need to fear the growing giant, before we fear we should be able to give a rational reason for why we have such fear.

Is China the friend who helps or the enemy that wants to rule the world?

There has been an escalation of fears regarding the intentions of China over the past few years with regards to their policies and global influence. The question is are these fears legitimate and how serious are they to the free world.

We need to have a deeper understanding of China to fully appreciate China’s intentions and how they plan…


Ethics in AI and DL — Who is Accountable?

Ethics cannot be discussed or practiced as a subject on its own nor can it be discussed and applied universally. Ethics can only be discussed and applied in relation to your philosophy or world view, this makes is an extraordinarily complex subject to address in a universal application because there are such divergent philosophies, so the challenge in AI and DL is how do you address ethics in a society that is not homogeneous and does not share the same basic philosophy. …


Lesson 2 was quite a bit more hectic than expected the volume of work was substantially more that lesson 1. The take-aways though are that Deep Learning is indeed far less daunting than expected. Seeing how relatively easy it is to set up data sets and train them was quite interesting, I have many questions that I hope will be answered later in the course since my experience of coding was far close to machine level than what Python is. …


learning station

My first coding was done on punch cards, something that most people today would not know about, but we graduated onto Pascal and then I left coding and pursued rather different career paths. I always wanted to get back into coding, but a variety of reasons stopped me mostly courses always assumed you either knew nothing or were a specialist, so I was either bored or lost.

The Idea of teaching by “playing the game” is used extensively in business called “on-the-job” training but I never found a course or person who could or would train me at a level…

Dennis Ash

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store