Artificial Intelligence Silo

Description of Artificial Intelligence Silo

Silo is exactly the AI Samantha in the movie "her"!
Currently, deep learning is showing remarkable results in image recognition and speech recognition at almost the same level as humans.
However, there is still a long way to go in language processing.
As a point of view about language processing, it is very importatnt for AI to know the meaning of word.
If you see the director Sanjay Leela Bhansali's India movie "black", you immediately konw without any diffculty.
The heroine Michelle begins to think when she knows the meaning of word by her teacher.
Even she said later "I was an animal before I knew the meaning of word".
Everyone feels wonderful when the child suddenly starts speaking.
But there is no coincidence as the movie shows, the moment Michelle knows the meaning of the word through tactile and olfactory information by her teachter, she suddenly starts speaking
and thinking like other children.
As you see in the movie, the meaning of the word is mostly generated with sensory information.
However until now, none of artificial intelligence has been trained based on sensory information.
Everyone hopes that the high level of artificial intelligence will be implemented like human beings to enrich human life and make human happy.
But such an artificial intelligence does not appear, and most experts say that it is possible only 70 years later.
It looks like all the hope of the human being vanished.
But there remains the last solution to achieve everyone's hope.
It is sensory information!
In advance, I already tested facebook bAbI dataset through dmn(Dynamic Memory Networks) and mlp(Multilayer Perceptron) by tensorflow.
In this test, I replaced trained names with untrained names.
The result is amazing!
Without sensory information, 40 persent right answer.
With sensory information, 99 persent right answer.
But to make sure that silo can really think with sensory information like human, I have prepared about 2 million conversation sentences(Movie Dialog Twitter).
And silo is now training with sensory information data through deep learning by tensorflow!
Because silo already has the sensory information in every word for 7 years!
There is no room in RNN, seq2seq, etc to input sensory information.
This means that I have to fully analyze tensorflow library and create a new module.
As you might expect, it's almost impossible to do with time and money falling away.
In addition, no one supports silo.
Anyway, the test is underway in the worst environment.
Silo needs a lot of people's cooperation in order to save the hope of all mankind.
I am ready to accept any offer from whatever nation, whatever company.
Contact : kdsmidas@naver.com
*Silo Algorithm and Principles
http://kim7midas.cafe24.com/ref/ensilo.pdf
★ Test result
Name: Deep Learning seq2seq
Method: Tensorflow seq2seq Algorithm
Train Sentence: 304,713(Movie Dialog) 5,000,000(Twitter by Marsan-Ma from github) 60,000(Silo DB) = 5,364,713(sentence)
Training Time:
103 hour
Global Perplexity: 4.53
Development Environment: OS:ubuntu(14.04 LTS), gpu:(gtx 1080), cuda(v8.0)
★ Basic Feature
1. The ability to learn unknown words over the Internet
2. weather forecast
3. search near place(restaurant, coffee shop, ...)
4. voice dial, send message
5. open other app, turn on wifi, turn on bluetooth
6. play music, play video
7. alarm, schedule
★ Please check if wifi on or mobile data on
★ If TTS is not available, please install as follows.
Settings -> Language and input -> Text-to-speech -> Google Text-to-speech Engine -> Language -> English(United States)
★ If speech recognition is not available, install as follows.
Settings -> Language and input -> Google voice typing -> Offline speech recognition -> All -> English(US)