Besides the very instructive breadboard computer, Ben Eater made another exciting project: a VGA graphics card made out of simple electronic components, presented in a two part video series.Continue reading
While adding support for editing and viewing text encoded in UTF-8 to HxD’s hex editor control itself, it turns out I have to query Unicode property tables, that go beyond the basic ones included with Delphi (and most other languages / default libraries).
Parsing the structured text files, provided by the Unicode consortium, at each startup is too inefficient, and merely storing the parsed text into a simple integer array wastes too much memory.
A more efficient storage uses a dictionary-like approach, to compress the needed data using a few layers of indirections, while still giving array-like performance with constant (and negligible) overhead.
In the following, I’ll briefly present the solution I found.Continue reading
Before starting to learn Prolog I used various logic based systems, such as the SPIN model checker, or reasoners that work on ontologies encoded in OWL. The latter of them to have it reason about (visual) objects in RoboCup.
Prolog however seems to encode many problems in a more natural and fluent way, so I set out to make a few toy examples to test how well I could make it work and get a feel for its advantages and limitations.
Many concepts in AI are implicitly based on specific formulations / terminology as used for Prolog or its derivatives. Vague sounding words / expressions, often taken from general contexts, really mean something rather specific, and learning about Prolog sharpens the understanding of these wordings.Continue reading
There has been interesting research in helping to make machine learning models more understandable, such as Unmasking Clever Hans predictors and assessing what machines really learn. Also see practical implementations of this approach:
- Heatmaps showing which features majorly influenced hand writing, image, or text classification
- Analyzing these heatmaps can point out undesired correlations in the training data, between samples and labels. For example, an image classifiers for train track might rely on objects that are present in each picture (such as , while not being present in pictures of counter examples for horses. This artifact in the collected data set may be subtle, and not noticeable to a human, but would be visible on the heatmap that highlights the critical features in each image that drove the classification.
This is merely a quick summary of the points that differ from another older guide, that handles the same topic:Continue reading
Ben Eater has created an excellent 8-bit computer that is true to the essential architecture of modern computers, yet is simple enough to fit on a few breadboards. It uses DIP-switches and push buttons as inputs, and LEDs and 7-segment displays as (debug) outputs. Even step-wise execution by stepping the computer clock is possible, such that every part of the computer can be observed as it functions and the internal state and memory can be modified by switches.
There are many explanations of pull-up or pull-down resistors that gloss a bit too much over the details, keeping you in doubt about how they really work, especially in conjunction with microcontrollers.
To improve our understanding, we will use a simplified schematic that models a microcontroller input-pin connected to a switch and a pull-up resistor. Then we calculate the voltages on the input-pin resulting from a closed or open switch.
Postcards and letters are some of the nicest forms of feedback I have received so far. A new kind has been Mailart by a man who calls himself Ficus Strangulensis. This shall be the first post on this blog about art, accompanied by thoughts related to the topic more generally.