AI projects
- Category: ML
- Project date: May, 2020
- Code URL: github
About
This AI Project repository contains a total of six projects 1. AI Snake Game 2.AI for Warehouse Robot 3.Autonoums Vehicle Self-Driving Car 4.Business Applications. 5.CNN Classifier 6.House Price Prediction
AI Snake Game
The game is pretty simple; it consists of a snake and an apple. We control the snake and our aim is to eat as many apples as possible. Every time our snake eats an apple, our snake gets larger by one tile. This means that the game is unbelievably simple at the beginning, but it gets gradually harder, to the point where it becomes a strategic game. Also, when controlling our snake, we can't hit ourselves, nor the borders of the board. This rather predictably results in us losing.
Snake Game
AI for Warehouse
AI has tremendous value to bring to transport and logistics, with self-driving delivery vehicles that speed up logistical processes. They're a huge boost to the economy through the e-commerce industry. The model we'll use for this will, of course, be Q-learning (we're saving deep Q-learning for the self-driving car). Q-learning is a simple, but powerful, AI model that can optimize the flows of movement in a warehouse, which is the real-world problem you'll solve here. The difference is that, this time, the maze will actually be the warehouse of a business. It could be any business: an e-commerce business, a retail business, or any business that sells products to customers and that has a warehouse to store large amounts of products to be sold.
Warehouse Model
Autonumous Self-Driving Cars
This project probably the most challenging, and most fun. We're literally about to build a self-driving car from scratch, on a 2D map, using the powerful deep Q-learning model. I think that's incredibly exciting!
The map
AI for Business – Minimize Costs with Deep Q-Learning
Using deep Q-learning solve a real-world business problem. With this, you'll be more than ready to add value to your work or business by leveraging AI. This project will provide you with a general AI framework, a blueprint containing the general steps of the process you have to follow when solving a real-world problem with deep Q-learning. We'll set up our own server environment, and we'll build an AI that controls the cooling and heating of the server so that it stays in an optimal range of temperatures while using the minimum of energy, therefore minimizing the costs.
CNN_Classifier
CNNs are mostly used with images or videos, and sometimes with text to tackle Natural Language Processing (NLP) problems. They are often used in object recognition, for example, predicting whether there is a cat or a dog in a picture or video. Here we ging to predict given image is belongs to what cat or dog.
Image Classification
Image Classification using CNN
House Price Prediction
What we want to do is predict how much a certain house might cost, based on some variables. In order to do so you need to follow these four steps:
1. Get some historical data on house sales; for this example, you'll use a dataset of about 20,000 houses in Seattle.
2. Import this data to your code while applying some scaling to your variables.
3. Build an Artificial Neural Network using any library—you'll use Keras, as it is simple and reliable.
4. Train your ANN and get the results. Now that you know the structure of your future code, you can start writing it.Since all the libraries that you'll use are available in Google Colab, you can easily use it to perform this task.
References