An invariant schema emerges within a neural network during hierarchical learning of visual boundaries
Elder, J. R.; Zheng, J.; Shimelis, L. B.; Rutishauser, U.; Lin, M. M.
Show abstract
Neural circuits must balance plasticity and stability to enable continual learning without catastrophic forgetting, a pervasive feature of artificial neural networks trained using end-to-end learning (e.g. backpropagation). Here, we apply an alternative, hierarchical learning algorithm to the cognitive task of boundary detection in video clips. In contrast to backpropagation, hierarchical training converges to a network executing a fixed schema and generates firing statistics consistent with single-neuron recordings from human subjects performing the same task. The hierarchically trained networks schema circuit remains invariant following training on sparse data, with additional data serving to refine the upstream representation.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- How well do models of visual cortex generalize to out of distribution samples? 96%
- Emergence of Emotion Selectivity in A Deep Neural Network Trained to Recognize Visual Objects 95%
- Pre-training artificial neural networks with spontaneous retinal activity improves motion prediction in natural scenes 94%
Similar papers in this journal
- Training a spiking neuronal network model of visual-motor cortex to play a virtual racket-ball game using reinforcement learning 94%
- Small hand-designed convolutional neural networks outperform transfer learning in automated cell shape detection in confluent tissues 93%
- Leveraging synthetic data produced from museum specimens to train adaptable species classification models 92%
Similar papers in this journal
- Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognition 93%
- Predictive coding with spiking neurons and feedforward gist signalling 93%
- Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks 92%
Similar papers in this journal
Similar papers in this journal
- Parallel hierarchical encoding of linguistic representations in the human auditory cortex and recurrent automatic speech recognition systems 94%
- Modeling neural coding in the auditory midbrain with high resolution and accuracy 93%
- COSIME: Cooperative multi-view integration with Scalable and Interpretable Model Explainer 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.