eegyolk.nn module

Copyright 2022 Netherlands eScience Center and Utrecht University. Licensed under the Apache License, version 2.0. See LICENSE for details.

This file contains functions designed to reproduce a neural net that worked with 2021 data.

class eegyolk.nn.NnOptimizer(loader, epochs=1500)

Bases: object

fit(model, n)

fit_model(n)

fully_connected_model(dropout=0.3, dense_max=512, dense_min=128, need_dropuot=True, nlayers=2)

input_shape = (450,)

model_name(n)

optimization_params = ({}, {'dropout': 0.5}, {'dense_max': 300, 'dense_min': 200}, {'need_dropuot': False}, {'nlayers': 3})

optimize()

predict(n)