| Peta::NN |
a small neural network, defined, trained and saved in Perl |
0.2610090 |
metacpan |
| Peta::NN::Backend |
the engines Peta::NN can compute on |
0.2610090 |
metacpan |
| Peta::NN::Backend::PDL |
Peta::NN on PDL ndarrays |
0.2610090 |
metacpan |
| Peta::NN::Backend::Plain |
Peta::NN on plain Perl arrays |
0.2610090 |
metacpan |
| Peta::NN::Backend::WebGPU |
Peta::NN on the graphics card |
0.2610090 |
metacpan |
| Peta::NN::Chain |
models put together into a model |
0.2610090 |
metacpan |
| Peta::NN::Codec |
characters to token indices, string pairs to edit labels |
0.2610090 |
metacpan |
| Peta::NN::Data |
records with named fields, to train models on and measure them by |
0.2610090 |
metacpan |
| Peta::NN::Fused |
micro models fused into one, as they are, the seams inside |
0.2610090 |
metacpan |
| Peta::NN::Inference |
load a trained model and get answers from it |
0.2610090 |
metacpan |
| Peta::NN::Job |
train a model until it meets given fidelity thresholds, at the smallest size that can |
0.2610090 |
metacpan |
| Peta::NN::Layer::Activation |
relu, tanh and sigmoid |
0.2610090 |
metacpan |
| Peta::NN::Layer::Dense |
fully connected layer |
0.2610090 |
metacpan |
| Peta::NN::Layer::Embed |
learned vectors for token indices |
0.2610090 |
metacpan |
| Peta::NN::Model |
train a micro model from string pairs, export it as a model file |
0.2610090 |
metacpan |
| Peta::NN::Optimizer |
SGD with momentum, and Adam |
0.2610090 |
metacpan |
| Peta::NN::Parallel |
independent pieces of work on several cores |
0.2610090 |
metacpan |
| Peta::NN::Pipeline |
models in series, and routed by a classifier |
0.2610090 |
metacpan |
| Peta::NN::RNG |
seeded random numbers that are the same on every perl |
0.2610090 |
metacpan |
