London
51.51° N, 0.13° W
kept since 2017
40 entries
Hi, I’m Husain.
I collect questions, take systems apart, and write about the pieces I find.
This is my public notebook: thoughts, research seeds, reading notes, experiments, and the occasional idea that refuses to leave me alone.
Some notes are polished. Some are still forming. I keep them here because thinking becomes clearer when it has somewhere to live.
since Jan 2026
still open
Question 1 (traceability). How do we build AI systems that can explain where their answers came from?
Remarks.A citation pasted underneath is not enough. I want a real trail of reasoning, evidence, uncertainty and context. The question sits between trustworthy AI, knowledge graphs, research methods and human judgement.
all 40 →
From the notebook
- N° 40
Garbage In: The Unglamorous Half of Machine Learning
Fifty rows of random numbers, labels with nothing to do with them, and a model that scores 95 per cent. A tour of the ways data misleads a model before it is trained, and the one mistake behind that number.
notemachine learning, data, statistics
- N° 39
Writing Knowledge Down
Tweety is a bird, so Tweety flies. Opus is a bird too. What happens when you try to give a machine a rule and an exception, why a graph of facts can resolve which Apple you meant, and the price of a language that can say anything.
noteai, knowledge representation, history of ai
- N° 38
Finding the Needle: How Retrieval Ranks Documents
A search engine does not read your documents when you ask. It read them once, in advance, and filed them under every word. Then comes the harder part: ranking what it finds, and checking that the score you trust is really a score.
notenlp, search, python
- N° 37
How a Convolutional Network Sees
A plain network and a convolutional one read the same handwritten digits, and one of them needs 127 times fewer adjustable numbers. Where the saving comes from, checked by hand, and what happens when you borrow, stretch or forge pictures to train with.
noteai, computer vision, neural networks
& elsewhere
Research, and the garden next door
My focus is moving towards AI, machine learning and deep learning, and above all the structures that make intelligent systems reliable, explainable and useful in the real world. I am less interested in treating AI as magic.
Keywords: trustworthy AI; traceability; human–AI collaboration; knowledge graphs; deep learning.
Research →Some thoughts stay here as notes. Some grow into lessons on Curio Synapse, my public learning garden for difficult ideas in science and technology.
This site is the notebook. Curio Synapse is the garden.
Visit Curio Synapse ↗1 active
Sometimes the best way to understand an idea is to build a small version of it. The workbench keeps prototypes, tools, experiments and systems that started as questions.
See what I’m building →