One of the key ideas in both robotics and neuroscience is that complex behaviour can arise from the interaction of many cooperating simple agents or modules. In this paper we suggest that this idea can be extended; just as combining simple agents may be important for complex behaviour, combining tasks is important for learning the parts themselves. In particular we show that combining classifications across different modalities can help solve the teaching signal dilemma and allow the development of task relevant classifications without external supervision. We recap some psychophysical and neurobiological data supporting the idea that information from different modalities can assist (or interfere) with classification in another modality and...
A long-standing goal in artificial intelligence is creating agents that can learn a variety of diffe...
A key question in studying consciousness is how neural operations in the brain can identify streams ...
This paper describes how agents can learn an internal model of the world structurally by focusing on...
One of the advantages of supervised learning is that the final error metric is available during trai...
Combining multi-modal information can ease classification. Neurobiologist Gerald Edelman postulated ...
Multi-modality is a fundamental feature that characterizes biological systems and lets them achieve ...
One key message in modern neuroscience is multimodality: the ability of uni-modal areas in the brain...
Why are sensory modalities segregated the way they are? In this paper we show that sensory modaliti...
Why are sensory modalities segregated the way they are? In this paper we show that sensory modalitie...
This dissertation focuses on the development of three classes of brain-inspired machine learning cla...
In psychology classification is studied as a separate cognitive capacity. In the field of autonomous...
Learners based on different paradigms can be combined for improved accuracy. Each learning method as...
AbstractFor humans to accurately understand the world around them, multimodal integration is essenti...
From infants to adults, each individual undergoes changes both physically and mentally through inter...
Human adaptive behavior requires continually learning and performing a wide variety of tasks, often ...
A long-standing goal in artificial intelligence is creating agents that can learn a variety of diffe...
A key question in studying consciousness is how neural operations in the brain can identify streams ...
This paper describes how agents can learn an internal model of the world structurally by focusing on...
One of the advantages of supervised learning is that the final error metric is available during trai...
Combining multi-modal information can ease classification. Neurobiologist Gerald Edelman postulated ...
Multi-modality is a fundamental feature that characterizes biological systems and lets them achieve ...
One key message in modern neuroscience is multimodality: the ability of uni-modal areas in the brain...
Why are sensory modalities segregated the way they are? In this paper we show that sensory modaliti...
Why are sensory modalities segregated the way they are? In this paper we show that sensory modalitie...
This dissertation focuses on the development of three classes of brain-inspired machine learning cla...
In psychology classification is studied as a separate cognitive capacity. In the field of autonomous...
Learners based on different paradigms can be combined for improved accuracy. Each learning method as...
AbstractFor humans to accurately understand the world around them, multimodal integration is essenti...
From infants to adults, each individual undergoes changes both physically and mentally through inter...
Human adaptive behavior requires continually learning and performing a wide variety of tasks, often ...
A long-standing goal in artificial intelligence is creating agents that can learn a variety of diffe...
A key question in studying consciousness is how neural operations in the brain can identify streams ...
This paper describes how agents can learn an internal model of the world structurally by focusing on...