git with Github 1. create a remote git git remote add origin (url) 2. clone files git clone (url) 3. generate the ssk key just follow the github 4. git add . add the dev to master 5. git commit
Left or Right in fMRI imaging ?
sometimes you get confused about how to interprate the result from the mri imaging in case on EEG data what is left and what’s right, smartly, most of software give a mark to show your right or left. I think
Gdansk DeepLearning summer school and FENS2018 Berlin
人生忽然间
人生忽然间 像风划过的脸 再见已不是昨天 我们亦不可能回到从前 天真烂漫的童年 热血激情的少年 风花雪月的青年 还有即将到来的中年 在路上 看不到曾经的风景 你只能一步一步的走 没有 什么都没有 这就是人生的无奈 生来一人 归去一人 所有涅槃和璀璨都是一瞬间 直到明天
Time Frequency in MEN and Visualization
In MNE time frequency is improtant for any further analysis for MEG EEG and fMRI here I address some from the toturials just for a remark. 1. Time Frequency functions in MNE all the output data will be the following
Exception: Error when checking model target: expected activation_6 to have shape (None, 10) but got array with shape (3, 1)
you will be surprised by this error in keras it is just beause you do not make the last layer as Dense(output_dim) or it will give this error, I’m so upset about this . model.add(Dense(4, activation=’softmax’)) here 4 is the
Tips for RNN in keras
In Keras we could use LSTM,GRU,SimpleRNN just as simple as in sklearn. here we mainly wonder to share some thing about LSTM,which could be divied into two subclass LSTM with statful or without stateful Input_shape, [samples,timesteps,input_dim] here, samples is the
a CNN for mnist from Keras
Gets to 99.25% test accuracy after 12 epochs (there is still a lot of margin for parameter tuning). 16 seconds per epoch on a GRID K520 GPU. ”’ from __future__ import print_function import keras from keras.datasets import mnist from keras.models
A deep NN for mnist in keras
from keras.models import Sequential from keras.layers import Dense,Activation,Dropout from keras.optimizers import RMSprop import keras from keras.datasets import mnist batch_size = 128 %% 批量训练的值 num_classes = 10 %%标签种类 epochs = 20 %% 重复训练的次数 # the data, split between train and test
Mutiple comparision Probelms for Neuronimaging data
The Multiple Comparisons Problem fMRI An important issue in fMRI data analysis is the specification of an appropriate threshold for statistical maps. If there would be only a single voxel’s data, a conventional threshold of p < 0.05 (or p