Search Results for "settings"

The supervised-reptile repository contains code associated with the paper “On First-Order Meta-Learning Algorithms”, which introduces Reptile, a meta-learning algorithm for learning model parameter initializations that adapt quickly to new tasks. The implementation here is aimed at supervised few-shot learning settings (e.g. Omniglot, Mini-ImageNet), not reinforcement learning, and includes scripts to run training and evaluation for few-shot classification. The fundamental idea is: sample a task, train on that task (inner loop), and then move the initialization parameters toward the adapted parameters (outer loop). Because Reptile is a first-order algorithm, it avoids computing second derivatives or full meta-gradients, making it computationally simpler while retaining good performance. ...

General purpose library (and some tools) that allows the construction of recursive deterministic/non-deterministic automaton from non-deterministic settings.

Sinalgo is a simulation framework for testing and validating network algorithms. It allows for quick prototyping and verification in freely customizable network settings. It is mainly suited for packet-oriented wireless networks.