The goal is to solve a diabetes classification problem using an Artificial Neural Network (ANN) optimized by a Genetic Algorithm, discovering the performance difference of different parameters of the ANN model and comparing this training method with additional optimizers like stochastic gradient descent, RMSprop, and Adam optimizer.
Data science can be summarized into five steps: capture, maintain, process, analyze, and communicate. First, we gather the data that has meaningful variables leading to appropriate classes. Then clean the data so that it is easy for a computer to read and process modeling. Next, we apply algorithms to train the model and test it using data acquired from the Kaggle dataset and analyze the model's performance. We then view the results and attempt to extract any relevant learning or information.
This is a multiclass image classification problem that uses convolutional neural network with TensorFlow (Keras api) to train on the Galaxy10 dataset.
This is a centuries-old game even played by Captain James Cook with his officers on his long voyages. Milton Bradley (now owned by Hasbro) published a version of this game called “Connect Four” in 1974. It is also called “Four-in-a-Row” and “Plot Four.” Two players play this game on an upright board with six rows and seven empty holes. Each player has an equal number of pieces (21) initially to drop one at a time from the top of the board. Then, they will take turns to play and whoever makes a straight line either vertically, horizontally, or diagonally wins.
In the traditional 3 by 3 tile puzzle, the number of inversions is used to prove its solvability. Looking at how each move changes the inversions of the puzzle, it is possible to find when the tile puzzle can reach any other state. To calculate the inversions, we transform the tiles row by row from a two-dimensional grid to a one-dimensional list. In this form, it is easier to solve for the…
To build an Image Search Engine that retrieves the most similar images from the database based on specific target images.
Given a query image (containing a specific instance) and a collection of images with different contents, we want to find the images that contain the same query instance from the collection.
The below images are two examples of query images (original + cropped).
The image below is the query result using ResNet transfer learning. Since I have ten query images, there are ten rows of images, with each row containing the ten most similar images to the query image. We…
With the emergence of online galleries and online fine-art markets, digitized fine-art painting collections have become demanding. Google Arts & Culture is an excellent example of an educational and recreational online platform that brings online fine art more accessible to people — letting people even immerse in the virtual art gallery through its VR technology. Another example is Artsy, which is an online fine-art brokerage. It utilizes a search system to link works of art based on their relationships with each other. In addition, many other applications require the techniques of fine-art classification. Therefore, the enhancement of the capabilities in…
The below tutorial will be divided into two parts — retrieve news information from the News API, and the generation of word clouds.
News API is a simple and easy-to-use API that returns JSON metadata for headlines and articles live all over the web right now.
First, head to News API to get the API key.