Search Results for author:
Found 7 papers, 4 papers with code
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.
A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions
We illustrate that incorporating predictive knowledge through an $\eta\gamma$-discounted SF model makes more efficient use of sampled experience, compared to either extreme, i. e. bootstrapping entirely on the value function estimate, or bootstrapping on the product of separately estimated successor features and instantaneous reward models.
Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece
We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them with the efficiency of gradient-based learning in recurrent neural networks.
Spike-based causal inference for weight alignment
Here we show how the discontinuity introduced in a spiking system can lead to a solution to this problem.
Inferring hierarchies of latent features in calcium imaging data
A key problem in neuroscience and life sciences more generally is that the data generation process is often best thought of as a hierarchy of dynamic systems.
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
Here we present results on scaling up biologically motivated models of deep learning on datasets which need deep networks with appropriate architectures to achieve good performance.
Towards deep learning with segregated dendrites
Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology.
