Search Results for author:
Found 13 papers, 4 papers with code
Theory of coupled neuronal-synaptic dynamics
In chaotic states with strong Hebbian plasticity, a stable fixed point of neuronal dynamics is destabilized by synaptic dynamics, allowing any neuronal state to be stored as a stable fixed point by halting the plasticity.
Dimension of activity in random neural networks
Neural networks are high-dimensional nonlinear dynamical systems that process information through the coordinated activity of many connected units.
The Implicit Bias of Gradient Descent on Generalized Gated Linear Networks
Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance.
Input correlations impede suppression of chaos and learning in balanced rate networks
To study this phenomenon we develop a non-stationary dynamic mean-field theory that determines how the activity statistics and largest Lyapunov exponent depend on frequency and amplitude of the input, recurrent coupling strength, and network size, for both common and independent input.
Credit Assignment Through Broadcasting a Global Error Vector
We prove that these weight updates are matched in sign to the gradient, enabling accurate credit assignment.
Neural population geometry: An approach for understanding biological and artificial neural networks
One approach to addressing this challenge is to utilize mathematical and computational tools to analyze the geometry of these high-dimensional representations, i. e., neural population geometry.
Training dynamically balanced excitatory-inhibitory networks
The construction of biologically plausible models of neural circuits is crucial for understanding the computational properties of the nervous system.
Feedback alignment in deep convolutional networks
We demonstrate that a modification of the feedback alignment method that enforces a weaker form of weight symmetry, one that requires agreement of weight sign but not magnitude, can achieve performance competitive with backpropagation.
full-FORCE: A Target-Based Method for Training Recurrent Networks
We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations.
Balanced Excitation and Inhibition are Required for High-Capacity, Noise-Robust Neuronal Selectivity
To evaluate the impact of both input and output noise, we determine the robustness of single-neuron stimulus selective responses, as well as the robustness of attractor states of networks of neurons performing memory tasks.
LFADS - Latent Factor Analysis via Dynamical Systems
Neuroscience is experiencing a data revolution in which many hundreds or thousands of neurons are recorded simultaneously.
Using Firing-Rate Dynamics to Train Recurrent Networks of Spiking Model Neurons
Recurrent neural networks are powerful tools for understanding and modeling computation and representation by populations of neurons.
Neurons and Cognition
Random Walk Initialization for Training Very Deep Feedforward Networks
We show that the successive application of correctly scaled random matrices to an initial vector results in a random walk of the log of the norm of the resulting vectors, and we compute the scaling that makes this walk unbiased.
