Unsupervised Discovery of Demixed, Low-Dimensional Neural Dynamics across Multiple Timescales through Tensor Component Analysis

Demixed principal component analysis of neural population data

Neurons in higher cortical areas, such as the prefrontal cortex, are often tuned to a variety of sensory and motor variables, and are therefore said to display mixed selectivity. This complexity of single neuron responses can obscure what information these areas represent and how it is represented. Here we demonstrate the advantages of a new dimensionality reduction technique, demixed principal...

Demixed Principal Component Analysis

In many experiments, the data points collected live in high-dimensional observation spaces, yet can be assigned a set of labels or parameters. In electrophysiological recordings, for instance, the responses of populations of neurons generally depend on mixtures of experimentally controlled parameters. The heterogeneity and diversity of these parameter dependencies can make visualization and int...

Max-weight scheduling across multiple timescales

Learning Multiple Timescales in Recurrent Neural Networks

Recurrent Neural Networks (RNNs) are powerful architectures for sequence learning. Recent advances on the vanishing gradient problem have led to improved results and an increased research interest. Among recent proposals are architectural innovations that allow the emergence of multiple timescales during training. This paper explores a number of architectures for sequence generation and predict...

Validating Computational Cognitive Process Models across Multiple Timescales

Model comparison is vital to evaluating progress in the fields of artificial general intelligence (AGI) and cognitive architecture. As they mature, AGI and cognitive architectures will become increasingly capable of providing a single model that completes a multitude of tasks, some of which the model was not specifically engineered to perform. These models will be expected to operate for extend...