Catalog ¶

NeuralNetwork Abstract and Links for each page

Basic Algorithms

Neural Network parameters
About neural network paramaters, weights and bias and matrix manipulation.

Auto Encoder
This tutorial introduces the auto encoder technique.

Introduction to the Loss Function
Introduction to two basic loss funcions, and related activation functions

Intro to Activation Function
We will introduce the basic activation function and its features.

Inside the Activation Function
Understanding the purpose and inside of activation function

Activation Function Types
In this tutorial, we will show the types of activation functions that are in ReNom.

Stochastic Gradient Descent(SGD) Settings
Effects of Stochastic gradient descent settings

Adagrad Optimization
Introduction to Adagrad Optimization

Adam Optimization
Introduction to Adam Optimization

Batch Normalization
How to use batch normalization with ReNom

Dropout
Dropout using fully connected neural network model to mnist.

Weight Decay
How to use weight decay with ReNom using fully connected neural network model to mnist.

Convolutional Neural Network(CNN)
In this chapter, we will introcduce the convolutional neural network(CNN) used in mainly computer vision tasks.

Precision and Recall
Precision and recall evaluation, using the “Adult Data Set.”

Correlation Coefficient and Coefficient of Determination
This is a simple introduction to correlation coefficients and coefficients of determination, using the Boston housing price dataset.


Preprocessing

Time Series Interpolation
Time series interpolation

Completion to numerical data and categorical data
Completion to numerical data and categorical data, using pseudo missing data

Merge the Categorical Data and the Mumeric Data
How to merge the categorical data and the numeric data using adult dataset.

Normalization and Standardization
Learning come to slow case, and prevent to use normalization and standardization.

Onehot Conversion for Categorical Data
The good point of onehot vector to learn

Preprocessing for Embedding Layers
We will explain preprocessing needed to use embedding layer on Renom.

Resize Preprocessing for Image Classification
Resize preprocessing for image classification using caltech dataset.

Zoom Preprocessing for Image Classification
Zoom preprocessing for image classification using caltech dataset

Flip Preprocessing for Image Classification
Flip preprocessing for image classification using caltech dataset

Rotate Preprocessing for Image Classification
Rotate preprocessing for image classification using caltech dataset

Shift Preprocessing for Image Classification
Shift preprocessing for image classification using caltech dataset

ColorJitter Preprocessing for Image Classification
ColorJitter preprocessing for image classification using caltech dataset

Crop Preprocessing for Image Classification
Crop preprocessing for image classification using caltech dataset


Data Visualization

Time Series Data

Image Data

Digit Image Classification
Digit image classification problem using fully connected neural network model to mnist.

Image classifier
An introduction of Convolutional neural network and how to use GPU.

image Binary Classification
Image binary classification problem using Convolution neural network model to Caltech 101

Neural Style Transfer
Implementation of “Image Style Transfer Using Convolutional Neural Networks.”

Using Pretrained Caffe model in ReNom
Loading the weights of pretrained Caffe model into ReNom model.

Object detection using YOLO
An example of object detection

Fully Convolutional Networks for Semantic Segmentation
This chapter introduces Fully Convolutional Network for Semantic Segmentation.

Conversion of a movie to a series of images
Conversion of a movie which is a kind of mp4 or avi to a series of images


Clustering

Regression

Generative Model

Embedding

ReNom DL

ReNom Basic Calculation using Auto Differentiation
This is an introduction of ReNom basic calculation using auto differentiation.

Sequential Model
An introduction to how to build a sequential model

Functional Model
An introduction of how to build functional model.

Concatenate Layer Output
Concatenate layer output using fully connected neural network model to mnist.

Trainer
An introduction of trainer function. Trainer function simplify training loop.

Saving and Loading Models
An introduction of saving and loading learned models.

Inference mode
Inference mode used for Dropout and Batch Normalization.

Hyperparameter Search
Hyperparameter search example, using the MNIST data


ReNom IMG

ReNom TAG

ReNom DP

TDA Basic

How to use ReNom TDA
An introduction of how to use ReNom TDA.

How to save Topology
An introduction of how to save topology.

Search Data
An introduction of searching topology data.

How to show Point Cloud
An introduction of show point cloud data.

How to clustering Point Cloud
An introduction of clustering point cloud data.

How to use 2D data
An introduction of using aleady dimension reduced data.

Convert Excel to CSV
An introduction of converting Excel data to csv file.

MNIST Dataset Mapping
An introduction of MNIST dataset mapping using ReNom TDA.

How to use ReNom TDA GUI
An introduction of how to use ReNom TDA GUI.


TDA Case Study

Database Interface