Topic: high-dimensional representations

Neural systems form high-dimensional representations that underpin their computational capabilities. Consequently, methods for quantifying representational similarity in neural representations have become a popular tool for identifying computational principles that are potentially shared across neural systems. These methods generally assume that neural responses are deterministic and static. However, responses of biological systems are noisy and dynamically unfold over time and these characteristics can have substantial influence on a system’s computational capabilities. We first show that exi

Training deep neural networks typically relies on backpropagating high-dimensional error signals---a computationally intensive and biologically implausible process. However, since most tasks involve low-dimensional outputs, we propose that low-dimensional error signals may suffice for effective learning. To test this hypothesis, we introduce a novel local learning rule based on Feedback Alignment that leverages indirect, low-dimensional error feedback to train large networks. Our method decouples the backward pass from the forward pass, enabling precise control over error signal dimensionality