Simulated Annealing

Simulated Annealing (SA) is a probabilistic technique used for finding an approximate solution to an optimization problem. To find the optimal solution when the search space is large and we search through an enormous number of possible solutions the task can be incredibly difficult, often impossible. Even with today’s modern computing power, there are still often too many possible solutions to consider. Therefore, we often settle for something that’s close enough to optimal solution when we may be not able to find the optimal solution within a certain time.

Introduction Machine Learning: K-nearest neighbors and Perceptron Learning Algorithm

Machine learning is a subfield of computer science where computers have the ability to learn without being explicitly programmed. List of the machine learning task:

• Supervised: Approximation where the all data is labeled and the algorithms learn to predict the output from the input data (training, cross validation and testing sets). We have two types of supervised problems:
• Regression: When the output variable is a real value, such as “dollars” or “age”.
• Classification: When the output variable is a category, such as “cat” or “dog” or “Tumor benign” and “Tumor malignant”. Regression vs Classification

• Unsupervised: Description where the all data is unlabeled and the algorithms learn to inherent structure from the input data.
• Clustering: A clustering problem is where you want to discover the inherent groupings in the data, such as grouping customers by purchasing behavior.
• Association: An association rule learning problem is where you want to discover rules that describe large portions of your data, such as people that buy X also tend to buy Y.

Summary of AlphaGo article: Mastering the game of Go with deep neural networks and tree search

Lately, I have been working on artificial intelligence. I have read the article of “Mastering the Game of Go with Deep Neural Networks and Tree Search Research” introduces how to combine the best of deep neural networks and search algorithms to achieve what was thought the impossible.

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence because of its enormous search space and the difficulty of evaluating board positions and moves.