mortenblorstad Goto Github PK

agtboost

Adaptive and automatic gradient boosting computations.

an_genetic_algoritm_example_using_shiny

An genetic game of sorts. A simple genetic algorithm that learns the player's preferance when it comes to size and color

automatic-relevance-determination

genetic-algorithm-from-scratch-using-r

Solving optimalization problem with a genetic algorithm using R

machine-learning-algorithms-from-scratch

maze-generation

Generate a maze from a grid using a depth-first search.

minesweeper

The game Minesweeper created in R

mortenblorstad.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

neural_networks-backpropagation

Creating a neural network and train it to predict animal types using gradient descent and backpropagation to optimize the network.

neuroevolution-of-neural-networks-from-scratch-in-r

Use neuroevolution to find an agent that can successfully classify animals. Create an population of neural networks and evaluates how well they perform. The best neural networks are selected for reproduction. Using crossover and mutation of parents' weights and biases, a new population of neural networks are created. This is repeated untill one find an individual that can successfully classify animals.

policysampler

Sample policies using MCMC/multicanonical sampling

stabletrees

Tree-based models are appealing for price modeling due to their high performance but they can be unstable. Due to competition between insurers, unstable models increase the risk that the overall premium is too small to cover the losses. The thesis propose various strategies for improving the stability of tree-based models.

stabletreeupdates

sudoku-solver

A sudoku solver algorithm using backtracking. The sudoku board is solved by assigning numbers to empty cells, one by one. Given the rules of sudoku, we check whether the number can be placed in the empty cell before assigned the number to the cell. If the number is valid we assign the number, and recursively check if this assignment leads to a solution or not. If it does not lead to a solution, we try the next number for the current empty cell. If none of the numbers from 1 to 9 leads to a solution, the is no solution to the board.

tic-tac-toe-ai-using-minimax-and-alpha-beta-pruning