Plasticity is the ability to adapt, the ability to shape a model. In order to better understand how models adapt in the face of ambiguity within a learning problem, we study specific aspects of plasticity of machine learning models in general and in artificial neural networks in particular. More precisely, we are interested in how previous experiences can shape how a model adapts to new learning problems such as when people learn to play badminton when they have previously played tennis. Neural network models have become a mainstay of commercially relevant machine learning applications such as image and speech recognition, as well as text processing. A common practice is to pre-train such models on a vast general corpus of data and then la...
The ability of the visual system for object recognition is remarkable. A better understanding of its...
Animals exhibit a remarkable ability to learn and remember new behaviors, skills, and associations t...
One of the most important and ubiquitous building blocks of machine learning is gradient based optim...
One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage...
Plastic neural networks have the ability to adapt to new tasks. However, in a continual learning set...
Plasticity, the ability of a neural network to quickly change its predictions in response to new inf...
[[abstract]]In non-batch learning systems, an index called plasticity is needed to indicate how easy...
Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain proc...
A growing body of research indicates that structural plasticity mechanisms are crucial for learning ...
A major goal of bio-inspired artificial intelligence is to design artificial neural networks with ab...
The search for biologically faithful synaptic plasticity rules has resulted in a large body of model...
Neumann K, Steil JJ. Optimizing Extreme Learning Machines via Ridge Regression and Batch Intrinsic P...
Synaptic plasticity is a major mechanism for adaptation, learning, and memory. Yet current models st...
Our brains are formed by networks of neurons and other cells which receive, filter, store and proces...
Short and long term plasticity as cause-effect hypothesis testing in robotic ambiguous scenario
The ability of the visual system for object recognition is remarkable. A better understanding of its...
Animals exhibit a remarkable ability to learn and remember new behaviors, skills, and associations t...
One of the most important and ubiquitous building blocks of machine learning is gradient based optim...
One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage...
Plastic neural networks have the ability to adapt to new tasks. However, in a continual learning set...
Plasticity, the ability of a neural network to quickly change its predictions in response to new inf...
[[abstract]]In non-batch learning systems, an index called plasticity is needed to indicate how easy...
Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain proc...
A growing body of research indicates that structural plasticity mechanisms are crucial for learning ...
A major goal of bio-inspired artificial intelligence is to design artificial neural networks with ab...
The search for biologically faithful synaptic plasticity rules has resulted in a large body of model...
Neumann K, Steil JJ. Optimizing Extreme Learning Machines via Ridge Regression and Batch Intrinsic P...
Synaptic plasticity is a major mechanism for adaptation, learning, and memory. Yet current models st...
Our brains are formed by networks of neurons and other cells which receive, filter, store and proces...
Short and long term plasticity as cause-effect hypothesis testing in robotic ambiguous scenario
The ability of the visual system for object recognition is remarkable. A better understanding of its...
Animals exhibit a remarkable ability to learn and remember new behaviors, skills, and associations t...
One of the most important and ubiquitous building blocks of machine learning is gradient based optim...