Recent Posts

Pages: [1] 2 3 ... 10
1
General Project Discussion / Re: Releasing full AGI/evolution research
« Last post by LOCKSUIT on October 23, 2020, 10:13:42 pm »
Also,

In some way, I feel there is 2 approaches to life/progress, and you could actually put it like this: you could take the Satanist or Religious approach. In the godly method, you re hopeful, but this is too hopeful, there is no grounding to reality, just a single book, or, what you could call "a thought". The satanist way is grim and truthful, too, but too little hope, they tell you we die, they promote death, they are crass and nasty. I like to stay in between :). I'm very hopeful so that I have goals, I may seem blissful at times or "detached and in the future already", but I'm also very grim dark and honest and know we are machines that will die if we don't evolve so that I can reachhhh those future goals, I may seem evil at times or "far in the past of history". In AI terms these 2 things are Frequency of observations, and reward, it causes you to say things that likely/ usually/ should happen. You predict your future. Will it be nearby death, or a distant future? The biggest rewards tends to be sparse, how long do meals or love making last? How long does victory last? We really want reward, but we really want frequency to walk you to the reward, and the walk needs reward to have a reason for the walking. When you lack one of these, you either don't reach the future because you can't walk or you can't reach the future because you have no clue where to walk.
2
General Project Discussion / Re: Releasing full AGI/evolution research
« Last post by LOCKSUIT on October 23, 2020, 06:09:42 pm »
This year has been my most productive year. I've learned to program in Python and make my first AI a year ago, I've much better understood KNN/K-Means, Random Forests, I already had the random forests idea but the KNN was amazing it took me 2 days to get so much out of it. I've made a dozen large discoveries and 100 micro discoveries. My AGI guide is much more on the way now and incredible than ever before. Among things I do every month I went through all of Kaggle courses in 2 days just now https://www.kaggle.com/learn/overview, I didn't bother with the code because its expensive time-wise to code but I still read all they said and understood it well. They always go through what others do and they certainly did a more thorough one they had reinforcement, NLP, computer vision, word2vec, backprop.....they didn't say so much in details but its clearer what they know (and share, they never share everything and clearly). And NLP and RL are not to be separated do not underestimate their relationships, computer vision is also very similar to NLP AI. I also went through lots of other readings of course, and generated my own discoveries of course. And I'll soon be creating images and code and vision-versions for my guide to AGI and an exotic AGI group so we can cover more ground and be surer/ clearer.
3
General Project Discussion / Re: Completed JesseAI's current *Emotion Database*
« Last post by frankinstien on October 23, 2020, 05:29:21 am »
How does your database compare with this approach? It's actually using an object oriented datamodel with an object oriented database or nosql database, which was built from scratch as well. The model allows for multiple class inheritance in real-time, so any changes in a base class can affect those classes that inherit from it, but those classes' existing data is never touched if the base class' is changed unless of course the data field's data type is changed or the field is removed, but adding new data fields is allowed to affect the classes that inherit from the base class.
4
General Project Discussion / Completed JesseAI's current *Emotion Database*
« Last post by JesseAIResearch on October 22, 2020, 06:51:08 pm »
I am happy to say that I have completed her current knowledge of human emotions. It's been some rough work, but it's finally completed for the time being. JesseAI is my homemade GOFAI or *Good Old Fashion Artificial Intelligence*. Completely written from scratch in C++.
5
General Robotics Talk / Re: Cyborg Dogs!
« Last post by Korrelan on October 22, 2020, 04:40:00 pm »
Drive a tone generator with the 4 TTL outputs.  Teach dog to tones.

4 Channel key Fob

 :)
6
General Robotics Talk / Re: Cyborg Dogs!
« Last post by Hopefully Something on October 21, 2020, 11:54:23 pm »
I've thought about attaching a small walkie-talkie to my dog's collar. She has the tendency to chase something like a squirrel, and then run "back" in completely the wrong direction when I call her due to floppy ear sound bouncing syndrome. With some kind of speaker on her, I could tell her to sit, or stay. It would be great to develop some minimal interference technologies to help with long distance pet communication. Possibly something smell based, maybe a treat dispenser. Maybe an AI assistant that could speak doggish, a canine Siri clipped on the collar to help out is certain situations.
7
General Robotics Talk / Cyborg Dogs!
« Last post by frankinstien on October 21, 2020, 08:41:43 pm »
Here's an article about using augmented reality headsets on dogs.

But what if we apply optogenetics to our Kanine friends? Then build interfaces that can connect to wifi, phone signals, etc, and even translate dog thoughts into words or at least teach dogs to think in words that they can communicate through the interface! Reminds me of the novel and movie A Boy and His Dog (1975 film), where the dog is telepathic.
8
General Chat / Re: What's everyone up to ?
« Last post by Don Patrick on October 20, 2020, 07:51:55 pm »
I've been making a simple OCR program this week to allow my virtual assistant to read text on my screen visually. The ways to get at text in other programs programmatically are restricted, and I wasn't about to install an 80Mb Tesseract neural network OCR program just to enhance my 2Mb program with a minor skill. I tried other OCR programs, but they were inaccurate for short snippets of text, and changed their results depending on how much space was above the letters(!). Anyway, so far so good, I'm using feature detection rather than try to match pixels.
9
General AI Discussion / Re: gen 3 skills for the LivinGrimoire
« Last post by yotamarker on October 20, 2020, 05:56:03 pm »
https://www.youtube.com/watch?v=yHVYTcpEnx0

UML draft

AbsCmdReq

DISkill

TheSkill // this is gen3
|
RegexUtil
DSkillUtil
PlayGround
Cloudianv2
MCodes
Person
SuperReplika

ReplikaMap
10
General AI Discussion / Re: A.I script writer
« Last post by spydaz on October 20, 2020, 02:10:46 pm »
Hiya Been a longtime posting ; but been working hard on various aspect of AI and focusing on coding the new programming languge and tools for creating converational AI and Knowledge learning from conversation and text etc.. lol.

After reading some posts: Its very interesting : story generation ; script generation ;Parts of speech tagging etc (code generation)<<<<Very important as the code generation / compiler / interpretor pattern <<<<< provides understanding on HOW? a domain specific language can be implemented ;

i have been looking at the possibility of generation of text ; scriptwriting ; Storytelling. I have had some minor sucesses and ideas as well as programming failures ;

I belive the concept is sound, and yet when generating the first set of sentences based upon Sentence structure i realised as the computer did not understand the relationships between the components of the generated sentences whilst gramatically correct were giberish.
With a more supervised approach ; phrase based? yes with such pre created phrases ; with HEADINGS such as "intorductin" (once upon a time, ....etc) a nice story could be generated by allowing for some random selection for NOUN Object such as names colors etc. ccreating simular yet differnt stories. leading to the understanding that preprogramed phrases works and yet left little scope for actual story generation , YES , Supervised works but is limited by the source phrases for each section of the story such as ENDINGS etc. (they lived happily ever after)
NOW, In understanding that storys regarding knowledge known about a THING? ie what is a cat? , based on stored data regarding a cat and its relations based on wordnet/verbnet/concept open minds and other such languge modeling; a dictionary response based on such collected data can be framed with such pre programed phrase structrues based on thier capture/ learning patterns, this generation allows for FORMAL sentences to be genearted about such a  thing.
AGAIN;  Regarding Conversational data collected ; this leads to scenario based sentence generation , this style of sentence generation has SOME preprogramed phrase structures also based on TIME/LOCATION/WHO/WHAT/WHY/WHEN. this temporal data ie: Short term memory has its own domain specific collected data and knowledge; sentence structure can be generated based on the collected grammar from sentences learned; ie: as we the human speaks we are unaware of the noun phrase and verb phrase relationship . the subject object / predicate... but in speach the AI can collect such phrases and store thier gramatical structures for reuse in sentence generation. this loosly based semi unsupervised/supervised learning also has pattern associtead and domain specific knwledge to represent;
In Combination of techniques a formal personality and an informal persoanlity can be produced (speech pattern based) . yes from the random sentence generator, to pattern based formal generator(domain specfic) to informal(user gramar based)(domain specific(temporal)).
this combination technique for Sentence generation Can use both RANDOM and FOCUSED Sentence generation to produce a script based on Goals headings and domain specific knowledge and grammar choice and selelction can be improved by neural network for comparisions against known human responses for the same domain specifi knowledge. the learning model would no use the output of the script generating algorithim for error correction or focused NLP of the final outputs expectations and human sounding response;

AGAIN;
This is only (MY EXPERIENCE) my personal insight!
Pages: [1] 2 3 ... 10

Scavengers by Improbable
by MikeB (AI News )
October 20, 2020, 06:51:05 am
Sony Patent Suggests PS5 Will Have a Chatbot Feature
by MikeB (AI News )
October 19, 2020, 09:32:40 am
efficiency breakthrough via mathematics
by infurl (AI News )
October 14, 2020, 09:47:44 am
deep drone
by infurl (Robotics News)
October 13, 2020, 03:08:39 am
cerebellum much more important than previously thought
by infurl (AI News )
October 13, 2020, 03:06:29 am
electronic neurons
by Hopefully Something (AI News )
October 02, 2020, 12:06:39 am
New model beats GPT3
by LOCKSUIT (AI News )
October 01, 2020, 11:54:25 am
Robotic vacuum cleaner news.
by Dat D (Robotics News)
September 29, 2020, 10:15:58 am

Users Online

149 Guests, 0 Users

Most Online Today: 168. Most Online Ever: 528 (August 03, 2020, 06:16:11 am)

Articles