Media
On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples
Praher, Verena, Prinz, Katharina, Flexer, Arthur, Widmer, Gerhard
Local explanation methods such as LIME have become popular in MIR as tools for generating post-hoc, model-agnostic explanations of a model's classification decisions. The basic idea is to identify a small set of human-understandable features of the classified example that are most influential on the classifier's prediction. These are then presented as an explanation. Evaluation of such explanations in publications often resorts to accepting what matches the expectation of a human without actually being able to verify if what the explanation shows is what really caused the model's prediction. This paper reports on targeted investigations where we try to get more insight into the actual veracity of LIME's explanations in an audio classification task. We deliberately design adversarial examples for the classifier, in a way that gives us knowledge about which parts of the input are potentially responsible for the model's (wrong) prediction. Asking LIME to explain the predictions for these adversaries permits us to study whether local explanations do indeed detect these regions of interest. We also look at whether LIME is more successful in finding perturbations that are more prominent and easily noticeable for a human. Our results suggest that LIME does not necessarily manage to identify the most relevant input features and hence it remains unclear whether explanations are useful or even misleading.
Directions in Abusive Language Training Data: Garbage In, Garbage Out
Vidgen, Bertie, Derczynski, Leon
Data-driven analysis and detection of abusive online content covers many different tasks, phenomena, contexts, and methodologies. This paper systematically reviews abusive language dataset creation and content in conjunction with an open website for cataloguing abusive language data. This collection of knowledge leads to a synthesis providing evidence-based recommendations for practitioners working with this complex and highly diverse data.
AIoT, A Popular Technology, Is Entering a Period of Rapid Development
HONG KONG, June 30, 2021 (GLOBE NEWSWIRE) -- MobiusTrend, the fintech market research organization, recently released a research report "AIoT, A Popular Technology, Is Entering a Period of Rapid Development". In recent years, AIoT has gradually become well known. AIoT, namely AI IoT, means the combination of AI and IoT. IoT collects the underlying data and AI processes and analyzes the data, so the two technologies promote each other to form a new fusion discipline. In fact, AIoT greatly empowers the real economy.
DSU to offer artificial intelligence degrees
A pair of artificial intelligence degrees are coming to Dakota State University. In March, the Board of Regents approved a bachelor of science degree in AI, which will be offered by the Beacom College of Computer and Cyber Sciences. Now another program, geared more toward the workplace, has the green light. The Board of Regents has given Dakota State University the okay to offer a bachelor of science in Artificial Intelligence in Organizations. Instead of focusing on the computer science side of AI, this degree will be offered through the College and Business and Information Systems.
The Role of Artificial Intelligence in the Publishing Industry - State of Digital Publishing
They have rolled out an AI-powered CMS (Content Management System) called Bertie. It's an artificially intelligent publishing platform, designed specifically for the in-house newsroom of journalists, expert contributor networks, and partners. It provides all of these people real-time trending topics to cover, recommending ways to make headlines more compelling and suggesting relevant imagery. They have rolled out an AI-powered CMS (Content Management System) called Bertie. It's an artificially intelligent publishing platform, designed specifically for the in-house newsroom of journalists, expert contributor networks, and partners. It provides all of these people real-time trending topics to cover, recommending ways to make headlines more compelling and suggesting relevant imagery.