Swarm plots of the validation loss for each of the compartments (basal, oblique, apical) of the three LBTW-trained models: Hard Parameter Sharing (MH), Multi-gate Mixture-of-experts (MMoE), and Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx).

مواد مشابهة

• Swarm plots of the generalisation loss for each of the compartments (basal, oblique, apical) of the neuron model for each of the three models: Hard Parameter Sharing (MH), Multi-gate Mixture-of-experts (MMoE), and Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx).
  حسب: Jonas Verhellen (19267988)
  منشور في: (2024)
• Mean weights from the experts in both Multi-gate Mixture-of-experts (MMoE; top row) and Multi-gate Mixture-of-experts with Exclusivity (MMoEEx; bottom row) after training the models on neural data, projected onto the different compartments of the cortical layer V biophysically-detailed neuron model.
  حسب: Jonas Verhellen (19267988)
  منشور في: (2024)
• Schematic representation of the architectures of the hard parameter model (left), the MMoE model (middle), and the MMoEEx model (right).
  حسب: Jonas Verhellen (19267988)
  منشور في: (2024)
• Inference speed of all three MTL architectures—Hard parameter sharing (MH), Multi-gate Mixture-of-experts (MMoE), and Multi-gate Mixture-of-experts with Exclusivity (MMoEEx)—After training on neural data generated by a biophysically-detailed model of a cortical layer 5 pyramidal neuron model compared to the classical NEURON simulation.
  حسب: Jonas Verhellen (19267988)
  منشور في: (2024)
• Smoothed time series plot of the evolution of the three diversity metrics (determinant, permanent and score) for two different training runs for both the MMoE (left) and the MMoEEx models (right).
  حسب: Jonas Verhellen (19267988)
  منشور في: (2024)