Machine Learning
Implementing K-Means Clustering Algorithm
AskAI
This technical problem asks the reader to implement a K-Means clustering algorithm from scratch. The input is a dataset consisting of N points in d-dimensional space, and a positive integer K. The output is K cluster centroids and a partition of the N points into K clusters.
Finding the Optimal Decision Boundary for a Binary Classification Problem
AskAI
There are many ways to find the optimal decision boundary for a binary classification problem, but the best way to do it is to use a method that minimizes the error on the training set.
Classifying handwritten digits from images
AskAI
The goal is to train a machine learning model to take an image of a handwritten digit and correctly identify the digit. The dataset consists of 28x28 grayscale images, with each pixel represented by a floating point value between 0 and 1.
Design a machine learning algorithm to predict ratings for new products.
AskAI
Design a machine learning algorithm that predicts ratings for new products, given a list of products with prices and ratings.
SVM for Linearly Separating Three-Class Dataset
AskAI
This technical problem deals with designing a support vector machine (SVM) that is able to linearly separate a three-class dataset. An example dataset is provided, along with the expected output of the SVM model.
"Design a machine learning algorithm to predict spam email."
AskAI
This problem asks for the design of a machine learning algorithm that can take in an email's text and label it as spam or not spam. The algorithm should output a predicted label for the email .
Implement a basic spam filter
AskAI
This problem asks for a machine learning algorithm that can take in a set of emails and classify them as spam or not spam.
Identifying Plagiarism in Documents
AskAI
This problem asks for the design of a machine learning algorithm to detect plagiarism in documents. The algorithm should be able to take in a document and compare it to a set of known documents, flagging any instances of plagiarism. The algorithm should also be able to handle different document formats (e.g. PDF, Word, text).
