Goto

Collaborating Authors

The available metrics in cvms

#artificialintelligence

Overall metrics simply look at whether a prediction is correct or not. Currently, cvms only has the Overall Accuracy. The Macro/Average metrics are based on one-vs-all evaluations of each class. Once done for all classes, we average the results. Note that this is sometimes referred to as one-vs-rest, as it is the current class against the rest of the classes.


Difficulty Rating of Sudoku Puzzles: An Overview and Evaluation

arXiv.org Artificial Intelligence

How can we predict the difficulty of a Sudoku puzzle? We give an overview of difficulty rating metrics and evaluate them on extensive dataset on human problem solving (more then 1700 Sudoku puzzles, hundreds of solvers). The best results are obtained using a computational model of human solving activity. Using the model we show that there are two sources of the problem difficulty: complexity of individual steps (logic operations) and structure of dependency among steps. We also describe metrics based on analysis of solutions under relaxed constraints -- a novel approach inspired by phase transition phenomenon in the graph coloring problem. In our discussion we focus not just on the performance of individual metrics on the Sudoku puzzle, but also on their generalizability and applicability to other problems.


Chatbots don't actually have an engagement problem

#artificialintelligence

Many people, journalists, and even companies who have invested in the chatbot industry have spoken out about the so-called chatbot engagement problem. The issue they are seeing is simple: Users initially play with a chatbot because it is fun and novel, but then quickly lose interest until, eventually, they go inactive (or quit using the bot altogether). Chatbots have an engagement problem! People do not engage with chatbots! Let's hold on for a minute and look at the bigger picture.


The Best Web Metric of them All

#artificialintelligence

Every time I see articles that focus on designing for new apps (like Gutenberg, WordPress' next-gen editor), the latest design trends (like flat design), or visuals that are supposedly "outside the box" (meaning non-standardized) I have to roll my eyes just a little bit. I'm not saying these things don't matter because they still do, but that they should they take a back seat to a few other things. You know, the ones that make you money. Before anything has been drawn or written for your website, you should know what the site's purpose will be. In other words, you should be able to describe who the website is for, and what you want those visitors to do after they've arrived.