An IBM made/pushed term, but that matches Ciro Santilli's general view of how we should move forward AGI.

Ciro's motivation/push for this can be seen e.g. at: Ciro's 2D reinforcement learning games.

Interesting layer skip architecture thing.

Apparently destroyed ImageNet 2015 and became very very famous as such.

catalog.ngc.nvidia.com/orgs/nvidia/resources/resnet_50_v1_5_for_pytorch explains:

CNN convolution kernels are not hardcoded. They are learnt and optimized via backpropagation. You just specify their size! Example in PyTorch you'd do just:as used for example at: activatedgeek/LeNet-5.

This can also be inferred from: stackoverflow.com/questions/55594969/how-to-visualise-filters-in-a-cnn-with-pytorch where we see that the kernels are not perfectly regular as you'd expected from something hand coded.

Two-element Boolean algebra, also known as Boolean algebra of two values, is a mathematical structure that deals with binary variables that can take on one of two values: typically represented as 0 and 1. This framework is foundational to digital logic and computer science.

A solution to Laplace's equation.

The term "means" can refer to several different concepts depending on the context. Here are a few common interpretations: 1. **Statistical Mean**: In mathematics and statistics, the mean is a measure of central tendency, typically calculated as the sum of a set of values divided by the number of values. For example, the mean of the numbers 2, 4, and 6 is (2 + 4 + 6) / 3 = 4.

In mathematics, the term "sign" refers to the indication of whether a number is positive, negative, or zero. It is typically represented using the following symbols: - Positive numbers: Represented by a plus sign (+) or no sign at all (e.g., +5 or 5). - Negative numbers: Represented by a minus sign (−) (e.g., −3). - Zero: The number 0 is neutral and does not carry a sign.

Alligation is a mathematical technique used in mixture problems to find the proportions of different ingredients or components in a mixture based on their individual costs or values and the cost or value of the mixture as a whole. It's particularly helpful in solving problems related to mixtures of liquids, solids, or other substances where each component has a different value.

Deep learning is the name artificial neural networks basically converged to in the 2010s/2020s.

It is a bit of an unfortunate as it suggests something like "deep understanding" and even reminds one of AGI, which it almost certainly will not attain on its own. But at least it sounds good.

As of my last knowledge update in October 2023, there isn't any widely recognized or notable figure or concept specifically named "Vitaly Khonik." It's possible that he could be an emerging figure in a specific field, such as science, art, or business, or a character in a work of fiction that has gained recognition since then.

"Arithmetic for Parents" is a book by Ron Aharoni, published in 2001. The book is designed to help parents understand the mathematics that their children are learning in school. It aims to bridge the gap between what is taught in schools and the understanding that parents might need to support their children's education. The book covers various mathematical concepts in a way that is accessible and engaging, often using practical examples and problems that parents might encounter in everyday life.

In arithmetic, "carry" refers to an essential concept that occurs during addition, particularly when adding multi-digit numbers. When the sum of digits in a given place value exceeds the base of the numbering system, a carry is generated. The excess value is then transferred to the next higher place value. For example, consider adding the two numbers 27 and 58: ``` 27 + 58 ----- ``` 1.