linkedin post 2019-04-03 05:16:31

Uncategorized
MORE EFFICIENT. "Code that's capable of altering its own instructions while it's still executing has been around for a while. Typically, it's done to reduce the instruction path length and improve performance, or to simply reduce repetitively similar code. But for all intents and purposes, there are no self-aware, self-improving AI systems today." https://lnkd.in/dp3ZKye View in LinkedIn
Read More

linkedin post 2019-04-06 03:43:09

Uncategorized
FRAGMENT FROM NATURE for this and next weekend contemplates lateral or horizontal gene transfer. This has been a fly in the ointment for traditional Mendelian genetics. Along with the idea of engulfment of entire organisms in an extreme form of symbiosis that separately gave rise to the mitochondria and the chloroplast, horizontal gene transfer has significantly mucked up tidy vertical inheritance trees. View in LinkedIn
Read More

linkedin post 2019-04-05 04:28:17

Uncategorized
FROM DATA TO LAWS. "We have demonstrated the discovery of physical laws, from scratch, directly from experimentally captured data with the use of a computational search. We used the presented approach to detect nonlinear energy conservation laws, Newtonian force laws, geometric invariants, and system manifolds in various synthetic and physically implemented systems without prior knowledge about physics, kinematics, or geometry." https://lnkd.in/dJJ9HmD View in LinkedIn
Read More

linkedin post 2019-04-03 05:13:07

Uncategorized
"SELF-MODIFYING CODE allows for code injection attacks such as “Stack smashing”, “Format string attacks” and many others. In these attacks, the injected code is written to a program’s memory as input data to which control is subsequently transferred. The majority of attacks of this kind are prevented today at the hardware level by marking writable memory pages as non-executable." https://lnkd.in/dHTSZ_H View in LinkedIn
Read More

linkedin post 2019-04-05 04:18:30

Uncategorized
FEW LIMITS. "Metalearning (or Meta-Learning) means learning the credit assignment method itself through self-modifying code. Metalearning may be the most ambitious but also the most rewarding goal of machine learning. There are few limits to what a good metalearner will learn." https://lnkd.in/dgfxJ_E View in LinkedIn
Read More