1
我应该使用多少个LSTM细胞?
是否有关于我应使用的LSTM电池的最小,最大和“合理”数量的经验法则(或实际规则)?具体来说,我与TensorFlow和property 有关的BasicLSTMCell有关num_units。 请假设我有以下定义的分类问题: t - number of time steps n - length of input vector in each time step m - length of output vector (number of classes) i - number of training examples 例如,训练示例的数量应该大于: 4*((n+1)*m + m*m)*c c单元数在哪里?我基于此:如何计算LSTM网络的参数数量?据我了解,这应该给出参数的总数,该总数应少于训练示例的数量。
12
rnn
machine-learning
r
predictive-modeling
random-forest
python
language-model
sentiment-analysis
encoding
machine-learning
deep-learning
neural-network
dataset
caffe
classification
xgboost
multiclass-classification
unbalanced-classes
time-series
descriptive-statistics
python
r
clustering
machine-learning
python
deep-learning
tensorflow
machine-learning
python
predictive-modeling
probability
scikit-learn
svm
machine-learning
python
classification
gradient-descent
regression
research
python
neural-network
deep-learning
convnet
keras
python
tensorflow
machine-learning
deep-learning
tensorflow
python
r
bigdata
visualization
rstudio
pandas
pyspark
dataset
time-series
multilabel-classification
machine-learning
neural-network
ensemble-modeling
kaggle
machine-learning
linear-regression
cnn
convnet
machine-learning
tensorflow
association-rules
machine-learning
predictive-modeling
training
model-selection
neural-network
keras
deep-learning
deep-learning
convnet
image-classification
predictive-modeling
prediction
machine-learning
python
classification
predictive-modeling
scikit-learn
machine-learning
python
random-forest
sampling
training
recommender-system
books
python
neural-network
nlp
deep-learning
tensorflow
python
matlab
information-retrieval
search
search-engine
deep-learning
convnet
keras
machine-learning
python
cross-validation
sampling
machine-learning