A type of artificial intelligence that focuses on designing systems that can learn from and make decisions based on data.
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 readingThe GENSIM project proposes an approach to generate rich simulation environments and expert demonstrations using large language models (LLM). It aims to address the challenge of task-level diversity in robotic…
Continue readingThe 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 readingThe article introduces WIMA (Window-based Model Averaging), a method designed to enhance the robustness and generalization capabilities of global models in Federated Learning (FL). FL aims to develop a shared…
Continue readingThe paper proposes an algorithm, Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI), for offline reinforcement learning with non-linear function approximation. The algorithm includes three innovative components: a variance-based weighted regression scheme,…
Continue readingThe study introduces H-InDex, a learning framework that uses visual representations from human hands to enhance robotic hand dexterity. This method includes three stages: pre-training representations with 3D human hand…
Continue readingThe 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 readingThe paper presents a novel approach to imitation learning (IL) in robotics called CasIL (Cognition-Action-based Skill Imitation Learning). CasIL introduces human cognitive priors into a dual cognition-action architecture, enabling robots…
Continue readingThe 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 readingThe 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 readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
