Reviews
Now Reading
RustNN
0
Review

RustNN

Overview
Synopsis

RustNN is a feedforward neural network library. The library generates fully connected multi-layer artificial neural networks that are trained via backpropagation. Networks are trained using an incremental training mode

Category

Artificial Neural Network Software

Features

•Backpropagation
•Incremental training mode

License

Proprietary Software

Pricing

Subscription

Free Trial

Available

Users Size

Small (<50 employees), Medium (50 to 1000 employees), Enterprise (>1001 employees)

Company

RustNN

What is best?

•Backpropagation
•Incremental training mode

PAT Rating™
Editor Rating
Aggregated User Rating
Rate Here
Ease of use
8.5
6.4
Features & Functionality
8.3
Advanced Features
8.5
Integration
8.3
Performance
8.4
Customer Support
7.4
Implementation
Renew & Recommend
Bottom Line

RustNN is a feedforward neural network library. The library generates fully connected multi-layer artificial neural networks that are trained via backpropagation. Networks are trained using an incremental training mode. RustNN can create a neural network with a given number of nodes in the input layer, the hidden layer and the output layer.

8.2
Editor Rating
6.4
Aggregated User Rating
1 rating
You have rated this

RustNN is a feedforward neural network library. The library generates fully connected multi-layer artificial neural networks that are trained via backpropagation. Networks are trained using an incremental training mode.

RustNN can create a neural network with a given number of nodes in the input layer, the hidden layer and the output layer. The network is trained on tuples of vectors where the first vector is the inputs and the second vector is the expected outputs.

Users can create a new neural network by passing a pointer to an array that specifies the number of layers and the number of nodes in each layer. When training the network incrementally it is trained in batches (updates weights only at the end of each epoch). Batch training can be parallelized and thus the Batch constructor takes a `u32`that specifies the number of threads to use when training the network. Users can specify options that dictate how a network will be trained.

When interacting with RustNN for the first time users may need to run some examples. They will find that `Incremental` means update the weights in the network after every example.

`Batch(t)` means run the network on all examples given and accumulate weight updates along the way but don't actually change the weights in the network until all of the examples have been run. Batch training can therefore be parallelized, so the `t` in the `Batch(t)` constructor specifies how many threads to use while training the network. Users can also log error rate if they so wish.

Filter reviews
User Ratings





User Company size



User role





User industry





Ease of use
Features & Functionality
Advanced Features
Integration
Performance
Customer Support
Implementation
Renew & Recommend

What's your reaction?
Love It
0%
Very Good
0%
INTERESTED
0%
COOL
0%
NOT BAD
0%
WHAT !
0%
HATE IT
0%