Search Results for author:
Found 13 papers, 6 papers with code
Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs
Training networks consisting of biophysically accurate neuron models could allow for new insights into how brain circuits can organize and solve tasks.
Attention for Causal Relationship Discovery from Biological Neural Dynamics
This paper explores the potential of the transformer models for learning Granger causality in networks with complex nonlinear dynamics at every node, as in neurobiological and biophysical networks.
How connectivity structure shapes rich and lazy learning in neural circuits
Through both empirical and theoretical analyses, we discover that high-rank initializations typically yield smaller network changes indicative of lazier learning, a finding we also confirm with experimentally-driven initial connectivity in recurrent neural networks.
A simple connection from loss flatness to compressed representations in neural networks
The generalization capacity of deep neural networks has been studied in a variety of ways, including at least two distinct categories of approach: one based on the shape of the loss landscape in parameter space, and the other based on the structure of the representation manifold in feature space (that is, in the space of unit activities).
Expressive probabilistic sampling in recurrent neural networks
We show that the firing rate dynamics of a recurrent neural circuit with a separate set of output units can sample from an arbitrary probability distribution.
Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators
Finally, we derive an in-silico implementation of ModProp that could serve as a low-complexity and causal alternative to backpropagation through time.
Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules
We first demonstrate that state-of-the-art biologically-plausible learning rules for training RNNs exhibit worse and more variable generalization performance compared to their machine learning counterparts that follow the true gradient more closely.
Comparison Against Task Driven Artificial Neural Networks Reveals Functional Properties in Mouse Visual Cortex
Several groups have developed metrics that provide a quantitative comparison between representations computed by networks and representations measured in cortex.
Recurrent neural networks learn robust representations by dynamically balancing compression and expansion
What determines the dimensionality of activity in neural circuits?
Data-Driven Discovery of Functional Cell Types that Improve Models of Neural Activity
Computational neuroscience aims to fit reliable models of in vivo neural activity and interpret them as abstract computations.
Dimensionality compression and expansion in Deep Neural Networks
Datasets such as images, text, or movies are embedded in high-dimensional spaces.
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression
We demonstrate the efficacy of a low rank version on visual cortex data and discuss the possibility of extending this to a whole-brain connectivity matrix at the voxel scale.
On stochastic differential equation models for ion channel noise in Hodgkin-Huxley neurons
We analyze three SDE models that have been proposed as approximations to the Markov chain model: one that describes the states of the ion channels and two that describe the states of the ion channel subunits.
Neurons and Cognition Quantitative Methods
