Cooperative Graph Neural Networks
The article ‘Cooperative Graph Neural Networks’ by authors from the University of Oxford proposes a new training method for graph neural networks. The authors view each node as a player…
Continue readingArtificial Intelligence
It is the subfield of computer science that focuses on creating systems capable of intelligent behavior, including problem solving, learning, adaptation, perception, and language understanding.
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
The authors introduce a new model for multivariate probabilistic time series prediction, designed to address tasks such as forecasting, interpolation, and their combinations. This model is based on copula theory…
Continue readingMerge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Sparsely activated Mixture-of-Experts (SMoE) has shown promise in scaling up the learning capacity of neural networks. However, problems like high memory usage and redundancy in experts arise due to duplication…
Continue readingElephant Neural Networks: Born to Be a Continual Learner
The research paper ‘Elephant Neural Networks: Born to be a Continual Learner’ by Qingfeng Lan and A. Rupam Mahmood, focuses on the issue of catastrophic forgetting in continual learning. The…
Continue readingRepresentation Engineering: A Top-Down Approach to AI Transparency
The article discusses an emerging area called Representation Engineering (RepE). This approach aims to increase the transparency of AI systems using insights from cognitive neuroscience. RepE focuses on population-level representations…
Continue readingMindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
This article presents MindShift, a new technique that uses large language models (LLMs) to address problematic smartphone use. The approach considers the user’s physical context, mental state, app usage behaviors,…
Continue readingAI enhances our performance, I have no doubt this one will do the same: The Placebo effect is robust to negative descriptions of AI
This study explores the placebo effect of AI in Human-Computer Interaction (HCI). It suggests that even when AI is described negatively, participants perform better if they believe they’re interacting with…
Continue readingMulti-Modal Financial Time-Series Retrieval Through Latent Space Projections
The paper presents a new framework for storing and retrieving financial time-series data. Rather than using traditional databases, the authors propose using deep encoders to store this data in a…
Continue readingPrototype Generation: Robust Feature Visualisation for Data Independent Interpretability
The article introduces Prototype Generation, a robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. It counters previous claims that feature visualisation algorithms are untrustworthy due…
Continue readingAI enhances our performance, I have no doubt this one will do the same: The Placebo effect is robust to negative descriptions of AI
The study explores the placebo effect of Artificial Intelligence (AI) in Human-Computer Interaction (HCI). The researchers found that the expectation of an AI-enhanced performance, even if it’s a sham, can…
Continue reading