In terms of machine learning we have been watching a millions of pattern is being stored inside an actor's memory. Whenever an actor is given a task, or challenged, it searches its memory and looks for a suitable pattern. How about we don't provide our actor any pattern, but allow access to the resources (like a human has) and then, our actor provides us at least a feasible solution?
case study: Google's alphaGo is thought to be a next gen. intelligent stuff, but as far as I am concerned it also stores moves from 150 previous games (roughly millions of moves) played by some top notch go players. It searches for the pattern, and plays accordingly. Is it such a big deal!!?? Isn't it showing the power of computation due to the gift of super computing!?
References:
https://research.googleblog.com/2016/01/alphago-mastering-ancient-game-of-go.html
https://deepmind.com/research/alphago/
https://news.ycombinator.com/item?id=11281226
Hi Ashique,
If I understand you correctly, then I can tell: it's difficult to obtain feasible solutions by working only with unsupervised learning methods. This can be due to the nature of this learning process where there are no clues to rely on, thereby evaluating unsupervised learning schemes is considered as a tough task.
Please note that, things can be similar with human being, i.e., without having references, it's difficult to make decisions.
HTH.
Samer
Dear Ashique,
I suggest you some links and attached files in topics.
- Unsupervised Learning - Université Stanford | Coursera
https://fr.coursera.org/.../machine-learning/.../unsupervised-learnin...
- Predictive modeling, supervised machine learning, and pattern ...
sebastianraschka.com/Articles/2014_intro_supervised_learning.html
-Hunting the Snark with Machine Learning, Artificial Intelligence, and ...
www.securityweek.com › Malware
-The AI & Machine Learning Glossary for Marketers - Drift Blog
blog.drift.com/machine-learning-explained
-Deep Reinforcement Learning: Pong from Pixels - Andrej Karpathy blog
karpathy.github.io/2016/05/31/rl/
-Machine Learning for Designers - O'Reilly Media
https://www.oreilly.com/learning/machine-learning-for-designers
- Machine Learning is Fun! – Medium
https://medium.com/.../machine-learning-is-fun-80ea3ec3c471
Best regards
- Badges
- Science topic
- Similar topics
- Engineering
- Computer Engineering