DAE neural net and Keras

Simon told me today he was ready to start building his own DAE (Denoising Auto Encoder) neural network. He said he would be using a documentation page about a machine learning library called Keras at blog.keras.io/building-autoencoders-in-keras.html. He found this documentation page completely on his own, by searching the web and digging into Python fora. I just watch him google something like “How can I install Keras 1.0?” and find GitHub discussions on the subject that guide him along. Or I see him type “How to install Python on Windows?” and follow the instructions at How-to-Geek. Eventually, he came up with a list of steps that he needed to complete in order to be able to install Keras (installing Python 3 (looking up why it should be 3 and not 2), installing PIP, installing Tensor Flow, etc). It didn’t work on a mac laptop, so he tried everything on a pc and it worked! Two steps required that he used terminal. It was amazing to see him plan ahead, search and implement (notoriously difficult) steps completely independently.

He has started working on the DAE tonight. Working on a node package that makes `manifest.json` files (for Chrome extensions) at the same time, so not sure he’ll finish soon. “Mom, I’ve got so many things to do! There are so many thoughts in my head!”



Just another day in graphs

Simon loves looking at things geometrically. Even when solving word problems, he tends to see them as a graph. And naturally, since he started doing more math related to machine learning, graphs have occupied an even larger portion of his brain! Below are his notes in Microsoft Paint today (from memory):

Slope of Line:

Slope of Line 15 November 2017

Steepness of Curve:

Steepness of Curve 15 November 2017

An awesome calculator Simon discovered online at desmos.com/calculator that allows you to make mobile and static graphs:

Desmos.com Polynomial 15 Nov 2017

Desmos.com Polynomial 15 Nov 2017 1

Yesterday’s notes on the chi function (something he learned through 3Blue1Brown‘s videos on Taylor polynomials):


Simon following The Math of Intelligence course by Siraj Raval:



à quatre mains

Here is Simon playing à quatre mains with his little sis, something he loves doing since she started piano lessons. She is not very keen on taking instructions, which upsets Simon enormously at times, but once they find the right tempo together, our whole world fills up with most beautiful vibes, making their loving friendship even more special.

Love for the absurd

Simon usually doesn’t like going places that much, but the trip to the Atomium in Brussels was a huge success, largely thanks to the Magritte exhibition hosted there at the moment. Simon liked the absurdity of Magritte’s juxtapositions and the idea that every object hides something else (behind it) from our sight. He kept talking about the meaning of the works as if he were a guide or a vlogger. The exhibition was very child friendly, everything was touchable and every painting was played with in a different manner.

Simon and Neva’s symbiosis

Simon is best friends with his little sis (who has just turned 6). He teaches her to make molecules


and she teaches him to play hopscotch


and to enjoy a walk in the evening


and to play together like kids do, including role-play (which Simon has finally mastered)


and he teaches her the tables of addition


and she teaches him to play outside


and he teaches her spatial orientation and more addition and subtraction with Magformers elements.




I often hear them say “I love you” to each other. Sometimes they talk about how things will be when they become old, really old. “I will probably die earlier than you,” – Simon said. “Because I’m two years older”. – “No, Simon, it doesn’t work that way”, – she answers. “Maybe not then. Maybe people won’t die anymore. Maybe there will be something left of me”.

Where are my compasses?


There’s been a lot of drawing going on here lately. And jokes, like in the video above. Yesterday, after he got distracted while trying to draw the exact tangent of a circle, Simon said: “I went off on another tangent. To find a tangent!”







Analysis and generation of text-based data. What else to do on vacation?

During the vacation, Simon worked on several programming projects playing with language and grammar, from Daniel Shiffman’s Programming from A to Z course at New York University. Those included creating a new context free grammar sentence generator, using a markov chain in a Google form, creating a diastic machine with JQuery and making a regular expressions tester in JavaScript.







Coding everywhere, swimming and popping giant balloons

A few more pics from the coding everywhere series:





Here Simon made a game especially for his sister:






Among the remaining favorites were reading (see an earlier post), swimming (and playing in the water) and, surprisingly still very high up on the list, popping giant balloons. City trips, walking and museums were way down below or even cancelled all together, even though the visit to Park Güell can be rated as successful.