Neural Networks Types and Main FeaturesFeedforward neural network  connections between nodes do not have a cycle  Multilayer perceptron (MLP)  has at least three layers of nodes  Reccurent neural network (RNN)  connections between units have a directed cycle  SelfOrganising Maps (SOM)  convert input data to low dimensional space  Deep Belief Network (DBN)  has connections between layers but not within layer  Convolutional Neural Network (CNN)  has one or more convolutional layers and then followed by one or more fully connected layers  Generative Adversarial Networks (GAN)  system of two neural nets, contesting with each other  Spiking Neural Netorks (SNN)  time information is processed in the form of spikes and there is more than one synapse between neurons  Wavelet neural network  use wavelet function as activation function in the neuron  Wavelet convolutional neural network  combine wavelet transform and CNN  Long shortterm memory (LSTM)  type of RNN, model for the shortterm memory which can last for a long period of time 
  Building Neural Network with Keras and Pythonfrom keras.models import Sequential
model = Sequential()
from keras.layers import Dense
model.add(Dense(units=64, activation='relu', input_dim=100))
model.add(Dense(units=10, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.SGD(lr=0.01, momentum=0.9, nesterov=True))
model.fit(x_train, y_train, epochs=5, batch_size=32)
model.train_on_batch(x_batch, y_batch)
loss_and_metrics = model.evaluate(x_test, y_test, batch_size=128)
classes = model.predict(x_test, batch_size=128)

Data Preparation for Input to Neural Networkfrom sklearn import preprocessing
def normalize_data(m, XData):
if m == "":
m="scalingno"
if m == "scalingno":
return XData
if m == "StandardScaler":
std_scale = preprocessing.StandardScaler().fit(XData)
XData_new = std_scale.transform(XData)
if m == "MinMaxScaler":
minmax_scale = preprocessing.MinMaxScaler().fit(XData)
XData_new = minmax_scale.transform(XData)
return XData_new

Cheat Sheets about Python and Machine Learning   Neural Network Applications and Most Used NetworksImage classification  CNN  Image recognition  CNN  Time series prediction  RNN, LSTM  Text generation  RNN, LSTM  Classification  MLP  Visualization  SOM 
Neural Net Weight Update MethodsAdam  based on adaptive estimates of lower order moments  AdaGrad  Adagrad is an adaptive learning rate method  RMSProp  adaptive learning rate method, modification of Adagrad method  SGD  Stochastic gradient descent  AdaDelta  modification of Adagrad to reduce its aggressive, monotonically decreasing learning rate  Newton method  second order method, is not used in deep learning  Momentum  method that helps accelerate SGD in the relevant direction  Nesterov accelerated gradient  evaluate the gradient at next position instead of current 

Cheatographer
Metadata
Favourited By
Comments
No comments yet. Add yours below!
Add a Comment