Thoughts and Theory

A gentle introduction to graph search algorithms and Markov Decision Processes

The ability to plan into the future seems to be one of the key characteristics of intelligence. Physical actions such as walking, cycling, doing sports, or driving requires immense coordination, and the best possible moves depend highly on the external environment (you have to adapt and change your strategy if there is a stone, an obstacle or an opponent in your way). Moreover, most of the things we do day to day — commuting, shopping, cooking, studying, working, etc. — involve both short and long-term planning. …

How to perform stochastic gradient ascent towards your goals

While maths, algorithms and data science can seem abstract and indifferent to our day-to-day worries and woes, I find it amusing how they can sometimes provide a perfect analogy to the problems and lessons we encounter in life. Here, I selected three observations that we can make from practices in machine learning and planning, which may give us hints on how we, in turn, can navigate the complexities of life to reach a near-optimal solution.

(Disclaimer: I have no intentions to claim that I know how to navigate life effectively — on the contrary, my weights are under-tuned and my…

Training of a 1000 epochs begins with a single gradient descent

It is fascinating how so many proverbs have endured the test of time and are still used in literature and daily conversations. The beauty of proverbs is that so many people can relate to them. This can be observed both from the abundance of synonymous proverbs and the number of proverbs that have spread cross-culture and cross-language.

As a research student who spends time with neural networks, I thought it would be fun to rephrase some of these well-known proverbs using AI terminology, and see how well they preserve the meaning of the original. The hope is that this will…

A big picture of odometry, localisation, mapping, feature matching and loop closure for non-roboticists

Remember the last time you’ve visited somewhere new? If you are reading this in 2020, you might have to rack your brain for those happy days. It may have been a holiday trip to an exotic place. You are excited to explore the area, check out all the nice restaurants and attractions. What would you do?

Yes, you read a map! (…or so it used to be)

Life has become too simplified nowadays with the intelligent little devices in our pockets, but let’s just imagine we are back in the stone ages. …

Photo by Julentto Photography on Unsplash

We all have different ways of keeping ourselves focussed and productive. I have seen many hardworking fellow students with a variety of strategies, and there are some habits I’ve adopted myself. I don’t pretend to have a comprehensive list of all the tricks and habits that can work. However, I do think that there is an underlying theme to these approaches. Here, I want to share what I believe to be some of the essentials to keep in mind.

Step 1: Know Your Strengths and Weaknesses

Different approaches work for different people, so it is important to sit down and assess yourself to figure out what works…

Let’s generate Shepard Scales from a PIC microcontroller in Assembly Language

In my previous article, I talked about the simplicity of Assembly Language and about the world’s smallest hobbyist computer — a PIC microcontroller. In this article, I want to pick up where we left off and introduce you to a fascinating illusion called Shepard Tones — an illusion of ever-ascending/descending scales — and how you can create that complex illusion with a simple PIC that can only emit ON-OFF signals.

The fundamentals of Shepard Tones

There is a family of auditory illusions called Shepard Tone. Hearing is believing. Here is a great example on YouTube:

In the first half of the video, the pitch…

The beauty of PIC microcontrollers

“Hello World!” — that is where we all start programming. At least, if you have a console. My entry point into this fascinating world was slightly different. In this hello world article, I want to share my first programming experience, which was literally in 0s and 1s.

I joined a science club in secondary school. There, I was immersed in synthesising ferrofluid — a liquid that is attracted to magnets. I managed to break a few beakers in the process. There was a student in the upper year who knew a lot about micro-controllers, and for our annual school festival…

Shu Ishida

DPhil student at University of Oxford, researching in computer vision and deep learning. Enjoys programming, listening to podcasts, and watching musicals.

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