ConvnetJS - 最佳配置

Question

我目前正在玩这个：https://github.com/marcoabreu/ConvNetJS-EMG-to-Force

它属于深度学习，是关于肌电信号与应用力之间的关系。

    layer_defs.push({type:'input', out_sx:windowSize, out_sy:8, out_depth:1});

layer_defs.push({type:'conv', sx:7, filters:16, stride:1, pad:2, activation:'relu'});
layer_defs.push({type:'pool', sx:2, stride:2});
layer_defs.push({type:'conv', sx:5, filters:32, stride:1, pad:2, activation:'relu'});
layer_defs.push({type:'pool', sx:3, stride:3});
layer_defs.push({type:'fc', num_neurons:64, activation: 'relu'});

layer_defs.push({type:'regression', num_neurons:1});

net = new convnetjs.Net();
net.makeLayers(layer_defs);

trainer = new convnetjs.Trainer(net, {method: 'adadelta', learning_rate: 0.01, l2_decay: 0.001, batch_size: 5})    

这是默认配置。你有什么建议改变以获得最佳数量的准确度？我应该添加哪些图层，我应该使用多少个过滤器？

这里有什么建议吗？