I love isometric views; they pack a bunch ( punch ?) of visual information and are great for sketching pseudo 3D views, making them programmatically on the other hand has always seemed daunting, at least to me, come along as I face my isometric fears and build one from scratch in python.

Here's a typical isometric Grid/Image and a simple approximation of what's going on which we will use throughout, starting from a simple square you rotate it 45° and then squish it so it is twice as wide as it is tall. 

I’ve been competing in the Numerai Quant competitions ( there are 2 ) for the past 3 years and thought it could be interesting to write a follow up to my previous two posts as a way to catch up…

Previous posts you might like:- Numerai walkthrough: Quantitative Analysis & Machine learning for fun and profit. The practical parts are now outdated, but the introduction explanation is still relevant. - Practical Keras Simple regression for the Numerai Tournament An up to date (late 2020) technical look at setting up a Neural Network for the tournament.

What is it again ?

In a nutshell Numerai…

At some point, you might need to make a grid or grid-like visual structure for a project or coding interview question (mazes, search). A grid is also the foundation for placing objects on a canvas surface in an orderly manner and more complex cases like isometric views and tiled games.

This article is meant to take us both from zero grids to Intermediate Gridology in a hopefully painless way.

Note: The code and concepts discussed here are somehow interchangeable between languages, but some languages provide a better native experience and primitives are needed for grids. …

Preface

There are plenty of articles describing Artificial General Intelligence (AGI) out there, the wiki on AGI is a great place to start, I think most definitions fit somewhere between describing an emulation of human cognitive abilities and defining intelligence by some well thought out premise: It can adapt to new circumstances, it can derive meaning and reason, it is logical, etc, etc.

Regardless of which flavor of AGI definition you like or agree with, what we still don’t have is an AGI and that’s because we simply can’t build one yet, but how can this be so ? What is…

How does your brain represent the environment ? The partial answer is the admittedly complex title which we will explore in this article.

Representation is a hard problem for both Neuroscience and AI and a good explanation of these terms I think is helpful if we are to build better AIs, this is my attempt.

Representations

A representation is simply that, the internal description of something, a thing, an idea or even a thought or feeling in general, but alas these later ones are very high in the hierarchy of representations and we don’t yet know exactly how they are formed…

As someone that spends most of the time thinking about Neuroscience, Artificial Neural Networks and Software the latest venture from Elon Musk: Neuralink on the surface ticks all the right boxes, so after their inaugural presentation I thought it would be fun to parse it and see what’s what. Care to join ?

The Pigs

Before delving into the details let’s go over the live demo they presented starting with the pigs:

It is always interesting to think about the next thing in AI, will it be something incremental or will it be something entirely different ? I like to think about the latter (but let’s briefly touch on the former) before moving on.

Incremental advances: The easy prediction here is to take current AIs/products and assume that they will gradually become better at what they do.The top tier of such current products are prediction AIs that employ Artificial Neural Networks (ANN) and algorithms for things like weather prediction, bureaucratic interactions, mundane tasks like search, not so mundane tasks like object…

What is it ?

If you work or are learning python, sooner or later you will bump into Numpy arrays, I’d venture that numpy, along with pandas dataframes are the workhorses of data as far as python is concerned. In layman terms Numpy arrays are data containers that can represent multiple dimensions and be queried and operated on, or if you prefer the official definition from the docs:

NumPy’s main object is the homogeneous multidimensional array. It is a table of elements (usually numbers), all of the same type, indexed by a tuple of non-negative integers. In NumPy dimensions are called axes.

From lists to Numpy Arrays

You might…