SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.00352 · NeurIPS · 2020

Meta-Consolidation for Continual Learning

Vineeth Balasubramanian, K Joseph

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 20 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
JosephKJ/merlin — 4 of 20
FunctionStatusWhere it lives
Metrics Ran JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("4f1c61003fbdaab9")
construct_state_dict_from_weights Ran JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("13ec5834ed19bd95")
gen_bar_updater Ran JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("69c291c8cf8a5818")
one_hot Ran JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("8431f92b5e9cab82")
CHUNKED_VAE Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("d4dbd015944bacde")
MNIST Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("b82ee827d83c2eff")
compute_accuracy Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("6d1affa42db4b765")
compute_offset Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("79feca99ba9abfe0")
decode_chunked_model Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("b0e208a3661a619b")
ensemble_and_evaluate Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("5813ce0c4f476a48")
ensemble_and_evaluate_cumulative_prior Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("da193d4ba7529139")
ensembled_prediction_for_a_task Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("f9eaee6cea9ea9a5")
evaluate_classification_model Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("d2dd1ab69b49be0e")
get_classification_loss Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("52adafc4af204ff6")
get_weights_from_chunked_vae Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("ee8b54e47e727fb2")
get_weights_from_chunked_vae_cumulative_prior Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("fd90c498ce78b6f1")
log Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("92a8f98b9d4d4a77")
recall Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("8116d3e7e4ec6a28")
train_block_chunk Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("4fdf6fab77d964a3")
train_vae Not yet run JosephKJ/merlin/lib/consolidate.py
pointer only (licence: NONE) · get_code("6d62cdee8d38351f")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We assume that weights of a neural network ψ, for solving task t, come from a meta-distribution p(ψ|t). This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.00352")
get_code_for_paper("2010.00352")
have("2010.00352")

Connect an agent — have() is free.