Show Menu

Neural Networks for Machine Learning Cheat Sheet by

Neural Networks for Machine Learning - showing neural networks types, applications, weight updates, python source code and links.
python     machine     learning     networks     neural     keras     convolutional     cnn

Neural Networks Types and Main Features

Feedfo­rward 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
Self-O­rga­nising 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 short-term memory (LSTM)
type of RNN, model for the short-term memory which can last for a long period of time

Building Neural Network with Keras and Python

from 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'))

              optimizer=keras.optimizers.SGD(lr=0.01, momentum=0.9, nesterov=True)), 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 Network

from sklearn import preprocessing

def normalize_data(m, XData):
    if m == "":
    if m == "scaling-no":
        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

Neural Network Applic­ations and Most Used Networks

Image classi­fic­ation
Image recogn­ition
Time series prediction
Text generation

Neural Net Weight Update Methods

based on adaptive estimates of lower order moments
Adagrad is an adaptive learning rate method
adaptive learning rate method, modifi­cation of Adagrad method
Stochastic gradient descent
modifi­cation of Adagrad to reduce its aggres­sive, monoto­nically decreasing learning rate
Newton method
second order method, is not used in deep learning
method that helps accelerate SGD in the relevant direction
Nesterov accele­rated gradient
evaluate the gradient at next position instead of current

Download the Neural Networks for Machine Learning Cheat Sheet

2 Pages

PDF (recommended)

Alternative Downloads

Share This Cheat Sheet!

Like this cheat sheet? Check out our sponsors! is a collection of tools to make your writing better. More readable content means higher conversion rates and better reader engagement. Measure website and document readability, measure keyword density and more!

Click Here To Get Started!



No comments yet. Add yours below!

Add a Comment

Your Comment

Please enter your name.

    Please enter your email address

      Please enter your Comment.

          Related Cheat Sheets

          Studying Cheat Sheet