Re: [agi] Genetic evolution of logic rules experiment

Neuroevolution of Augmenting Topologies (NEAT): https://www.youtube.com/watch?v=b3D8jPmcw-g -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T77af318d4abfa8a8-M8ee799e67846f9845cb23741 Delivery options: https://a

Re: [agi] Genetic evolution of logic rules experiment

On Tue, Oct 1, 2019, 9:21 AM YKY (Yan King Yin, 甄景贤) < generic.intellige...@gmail.com> wrote: > > From the data of this model, it would be *inferred* that "John is > probably unhappy / heart-broken". It is this inference mechanism that is > very mysterious to us. > Human reproductive behavior is

Re: [agi] Genetic evolution of logic rules experiment

On Tue, Oct 1, 2019 at 7:48 AM Brett N Martensen wrote: > Matt is right - Logic needs to be grounded on experiences. > > http://matt.colorado.edu/teaching/highcog/readings/b8.pdf That's a good paper, I will read it in details later. I made a mistake earlier. When the brain thinks about "John

Re: [agi] Genetic evolution of logic rules experiment

> We also know from 35 years of experience (beginning with Cyc) that logic based knowledge representation is not a path to AGI I'm begging to differ! But then you already know that I do, I guess :-) On Mon, 30 Sep 2019 at 23:47, Matt Mahoney wrote: > Boolean logic is a subset of neural networks

Re: [agi] Genetic evolution of logic rules experiment

On Mon, Sep 30, 2019 at 11:04 PM Stefan Reich via AGI wrote: > Uh... so where is it on GitHub? > The code is here (still under development): https://github.com/Cybernetic1/GILR There are further explanations in the README and some screenshots. 😊 -- Arti

Re: [agi] Genetic evolution of logic rules experiment

Not to argue with Matt's well-founded main point with this pedantic nit: Any deterministic dynamical system can be simulated to an arbitrary degree of precision with a finite directed *cyclic* NOR (or NAND) graph.  There was even some guy at the second IJCNN in San Diego (1990) with a "trainable

Re: [agi] Genetic evolution of logic rules experiment

Matt is right - Logic needs to be grounded on experiences.  http://matt.colorado.edu/teaching/highcog/readings/b8.pdf -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T77af318d4abfa8a8-Mf5918de07e97143626ca339f De

Re: [agi] Genetic evolution of logic rules experiment

Boolean logic is a subset of neural networks. A single neuron can implement any logic gate. Assume the output is clamped between 0 and 1. A and B = A + B - 1. A or B = A + B. Not A = -A + 1. But first order logic is not so simple. We also know from 35 years of experience (beginning with Cyc) that

Re: [agi] Genetic evolution of logic rules experiment

Neuronal Pools and Neural Processing: https://www.youtube.com/watch?v=QJ8AW5pi2T4 -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T77af318d4abfa8a8-M2abd8536631e80f94461bc91 Delivery options: https://agi.topicb

Re: [agi] Genetic evolution of logic rules experiment

Uh... so where is it on GitHub? On Sun, 22 Sep 2019 at 01:41, YKY (Yan King Yin, 甄景贤) < generic.intellige...@gmail.com> wrote: > Anyone interested in genetic evolution approach to learn logic rules? > Each logic rule would be encoded as a gene (individual) and the whole set > of rules evolve as a

Re: [agi] Genetic evolution of logic rules experiment

On 9/27/19, Steve Richfield wrote: > YKY, > > The most basic function of neurons is process control. That is where > evolution started - and continues. We are clearly an adaptive control > system. Unfortunately, there has been little study of the underlying > optimal "logic" of adaptive control sy

Re: [agi] Genetic evolution of logic rules experiment

On Fri, Sep 27, 2019 at 12:38 AM James Bowery wrote: > On Tuesday, September 24, 2019, at 11:46 PM, YKY (Yan King Yin, 甄景贤) wrote: > > My idea is just a general learning algorithm that can be applied to both > supervised and unsupervised situations. > > > What you are looking for is a general los

Re: [agi] Genetic evolution of logic rules experiment

On Tuesday, September 24, 2019, at 11:46 PM, YKY (Yan King Yin, 甄景贤) wrote: > My idea is just a general learning algorithm that can be applied to both > supervised and unsupervised situations. What you are looking for is a general lossless compression algorithm and it has been proven such does n

Re: [agi] Genetic evolution of logic rules experiment

UL is auto sorting, you have a goal still but that's it. SL is like telling it to match some data or gather new data. RL is similar but after training you know what decisions you have and decide at each step, with probabilities. -- Artificial General Intelli

Re: [agi] Genetic evolution of logic rules experiment

James Bowery wrote: If you are acting on the environment to obtain information, you are "supervised" by the environment and your action involves decision theory parameterized by a value function in an explore/exploit tradeoff.?? ??This corresponds to engineering/technology and it is what livin

Re: [agi] Genetic evolution of logic rules experiment

How is genetic evolution going to do unsupervised learning  YKY?  I have my method of doing unsupervised learning. very advanced.  Unsupervised learning at the moment in the wold of artificial intelligence is still very  primitive.  -- Artificial General I

Re: [agi] Genetic evolution of logic rules experiment

Thanks to Tim Tyler and James Bowery's explanations 👍 My idea is just a general learning algorithm that can be applied to both supervised and unsupervised situations. I am focusing on how to learn logic rules efficiently. The logic rules would explain a set of data (such data is also expressed a

Re: [agi] Genetic evolution of logic rules experiment

If you are acting on the environment to obtain information, you are "supervised" by the environment and your action involves decision theory parameterized by a value function in an explore/exploit tradeoff.   This corresponds to engineering/technology and it is what living things do. If your le

Re: [agi] Genetic evolution of logic rules experiment

On 2019-09-24 18:44:PM, YKY (Yan King Yin, 甄景贤) wrote: On Wed, Sep 25, 2019 at 12:03 AM doddy > wrote: how effecient is it compared to self supervised learning? You mean unsupervised?  I am not seeing much of a difference between the 2 notions. "Self-supervi

Re: [agi] Genetic evolution of logic rules experiment

On Wed, Sep 25, 2019 at 12:03 AM doddy wrote: > how effecient is it compared to self supervised learning? > You mean unsupervised? I am not seeing much of a difference between the 2 notions. The same genetic algorithm idea can be used to learn / evolve a set of logic rules to "explain" or pre

Re: [agi] Genetic evolution of logic rules experiment

how effecient is it compared to self supervised learning? On Sat, Sep 21, 2019 at 6:41 PM YKY (Yan King Yin, 甄景贤) < generic.intellige...@gmail.com> wrote: > Anyone interested in genetic evolution approach to learn logic rules? > Each logic rule would be encoded as a gene (individual) and the whol

[agi] Genetic evolution of logic rules experiment

Anyone interested in genetic evolution approach to learn logic rules? Each logic rule would be encoded as a gene (individual) and the whole set of rules evolve as a entire population. This is the so-called cooperative evolution approach. My code is about 70-80% completed. It's in Python, on Git