Search Results for author:
Found 8 papers, 2 papers with code
Intrinsic Biologically Plausible Adversarial Robustness
Artificial Neural Networks (ANNs) trained with Backpropagation (BP) excel in different daily tasks but have a dangerous vulnerability: inputs with small targeted perturbations, also known as adversarial samples, can drastically disrupt their performance.
Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
"Forward-only" algorithms, which train neural networks while avoiding a backward pass, have recently gained attention as a way of solving the biologically unrealistic aspects of backpropagation.
Can Machines Imitate Humans? Integrative Turing Tests for Vision and Language Demonstrate a Narrowing Gap
To address this question, we turn to the Turing test and systematically benchmark current AIs in their abilities to imitate humans in three language tasks (Image captioning, Word association, and Conversation) and three vision tasks (Object detection, Color estimation, and Attention prediction).
Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass
Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer.
Modeling the Repetition-based Recovering of Acoustic and Visual Sources with Dendritic Neurons
Furthermore, we extend the study to investigate the properties of segregation on task settings not yet explored with human subjects, namely natural sounds and images.
Learning in Deep Neural Networks Using a Biologically Inspired Optimizer
Here, we propose a novel biologically inspired optimizer for artificial (ANNs) and spiking neural networks (SNNs) that incorporates key principles of synaptic integration observed in dendrites of cortical neurons: GRAPES (Group Responsibility for Adjusting the Propagation of Error Signals).
Fooling the primate brain with minimal, targeted image manipulation
Here we propose an array of methods for creating minimal, targeted image perturbations that lead to changes in both neuronal activity and perception as reflected in behavior.
Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection
We describe an SNN training procedure that achieves low spiking activity and pruning algorithms to remove 85% of the network connections with no performance loss.
