Related papers: SERKET: An Architecture for Connecting Stochastic …
This paper describes a framework for the development of an integrative cognitive system based on probabilistic generative models (PGMs) called Neuro-SERKET. Neuro-SERKET is an extension of SERKET, which can compose elemental PGMs developed…
The ability to recognize human partners is an important social skill to build personalized and long-term human-robot interactions, especially in scenarios like education, care-giving, and rehabilitation. Faces and voices constitute two…
Our world is being increasingly pervaded by intelligent robots with varying degrees of autonomy. To seamlessly integrate themselves in our society, these machines should possess the ability to navigate the complexities of our daily routines…
Recent advances in large-scale machine learning have produced high-capacity foundation models capable of adapting to a broad array of downstream tasks. While such models hold great promise for robotics, the prevailing paradigm still…
Long-term autonomy of robotic systems implicitly requires dependable platforms that are able to naturally handle hardware and software faults, problems in behaviors, or lack of knowledge. Model-based dependable platforms additionally…
Artificial intelligence built on large foundation models has transformed language understanding, vision and reasoning, yet these systems remain isolated and cannot readily share their capabilities. Integrating the complementary strengths of…
This paper introduces our approach to building a robot with communication capability based on the two key features: stochastic neural dynamics and prediction error minimization (PEM). A preliminary experiment with humanoid robots showed…
Coreset, which is a summary of the original dataset in the form of a small weighted set in the same sample space, provides a promising approach to enable machine learning over distributed data. Although viewed as a proxy of the original…
When designing robots to assist in everyday human activities, it is crucial to enhance user requests with visual cues from their surroundings for improved intent understanding. This process is defined as a multimodal classification task.…
Large-scale neuroscience is generating rich datasets across animals, brain areas and behavioral contexts, yet our modeling efforts remains fragmented across isolated experiments. We argue that understanding behavior requires integrative…
Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…
We present a system enabling a modular robot to autonomously build structures in order to accomplish high-level tasks. Building structures allows the robot to surmount large obstacles, expanding the set of tasks it can perform. This…
Deep learning enabled semantic communications have shown great potential to significantly improve transmission efficiency and alleviate spectrum scarcity, by effectively exchanging the semantics behind the data. Recently, the emergence of…
A number of machine learning models have been proposed with the goal of achieving systematic generalization: the ability to reason about new situations by combining aspects of previous experiences. These models leverage compositional…
Before applying data analytics or machine learning to a data set, a vital step is usually the construction of an informative set of features from the data. In this paper, we present SMARTFEAT, an efficient automated feature engineering tool…
Robots are increasingly common in industry and daily life, such as in nursing homes where they can assist staff. A key challenge is developing intuitive interfaces for easy communication. The use of Large Language Models (LLMs) like GPT-4…
Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters but also a suitable model structure. Recent work on the discovery of…
Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, e.g., GPT-3 and Swin Transformer. Although originally…
This study focuses on Embodied Complex-Question Answering task, which means the embodied robot need to understand human questions with intricate structures and abstract semantics. The core of this task lies in making appropriate plans based…
The Artificial Intelligence field is flooded with optimisation methods. In this paper, we change the focus to developing modelling methods with the aim of getting us closer to Artificial General Intelligence. To do so, we propose a novel…