As blockchain and cryptocurrency development has continued to excel in the past few years, more people are wanting to develop cryptocurrencies of their own. The reasons behind this vary; financial flexibility for a unique startup, rewarding users utilizing one’s newly launched software, and the ability to practice developing blockchains. Regardless…

Solving Kaggle’s Titanic Machine Learning Dataset — Kaggle’s Titanic Machine Learning Dataset––a classic open-source introduction to the realm of machine learning. While this may be a beginner project, there is still a leaderboard (it is captivating to see yourself rank up as you continue to work on your code). To start, it is required that you download…

Kaggle, a Google subsidiary, is a community of machine learning enthusiasts. This particular project launched by Kaggle, California Housing Prices, is a data set that serves as an introduction to implementing machine learning algorithms. The main focus of this project is to help organize and understand data and graphs. This…

Background Information Q-Learning is generally deemed to be the “most simple” reinforcement learning algorithm. I find myself agreeing with this statement. In another paper, I discussed the use of Q-Learning compared to Deep Q Networks. So, I will pull the information that discussed what Q-Learning is, the positives and negatives…

For image recognition tasks, using pre-trained models are great. For one, they are easier to use as they give you the architecture for “free.” Additionally, they typically have better results and typically require need less training. To see a real application of this theory, I will be using Kaggle’s CatVSDogs…

Abstract. Using a classic environment from OpenAI, CarRacing-v0, a 2D autonomous vehicle environment, alongside a custom based modification of the environment, a Deep Q-Network (DQN) was created to solve both the classic and custom environments. Through the use of a Resnet18 pre-trained architecture and a custom made convolutional neural network…