Differences

This shows you the differences between two versions of the page.

--- people:demitri_maestas:project [2017/09/13 00:51] – created chucho2
+++ people:demitri_maestas:project [2017/09/13 04:33] (current) – chucho2
@@ Line 1: / Line 1: @@
-test
+====== Blue Sky Idea(s) ======
+[[people:demitri_maestas|<-- Return to Demitri's page]]
+----
+==== An Artificial Neuron ====
+Evolution has done so much of the dirty work for us; 3.5 billion years of attempts at creating robust living systems {{ :people:demitri_maestas:project:assets:neuron.jpg?direct&100|}}that work on a scale that begins inside of a membrane in a single cell and stretches out to the stratosphere. The industry-based data storage model in our current machines holds no similarity to the trials and tribulations that these living systems have endured, which is odd considering the fact that **Mother Nature has 3.5 billion years of design under her belt, where as we have only had a Von Neumann machine for about 80 years.** We need to be thinking about robust storage of information not in memory addresses based on a data structure, but instead, contained within the axons of artificial neurons that make mimic the design structure of the most robust //organic// hard drive we have; The human brain.
+==== Robustness in Machine Learing ====
+We've all seen what machine learning is capable of and the things it can help us do. Just take a look at this awesome machine learning example that Youtuber "SethBling" has designed to play the first level of Super Mario World:{{ youtube>qv6UVOQ0F44?large }}
+Machine Learning is an exciting field in computer science, but what is the robust first approach to machine learning? How can we use the same principals in the MFM to accomplish the same results? Is it even possible to accomplish machine learning, or do we need to think of a new form of computation for robust results?
+----
+==== Common Algorithms as a Process ====
+Machine learning is great at patterns. The Machine Learning algorithms we use today can become the best players in{{ :people:demitri_maestas:project:assets:tic.png?nolink&100|}} the world at beating Sonic The Hedgehog games, recognizing an "a" amidst 200 different styles of calligraphy, and solving complex math problems.
+But what about the Min-Max paradigm that is implemented to solve tic-tac-toe?
+The one that can keep up with any decent human player, because it becomes more intelligent with the more resources it is allotted?
+What is our robust equivalent?
+**How would the MFM //play// tic-tac-toe with a human opponent?**
+We need to start thinking with portals....
+----
+ --- //[[chucho2@unm.edu|Demitri D Maestas]] 2017/09/12 22:27//
+Pictures Used:
+https://www.quora.com/What-are-the-parts-of-the-neuron-and-their-function
+http://react-tictactoe.stefanwille.com/