Generative Continual Concept Learning

Authors: Mohammad Rostami, Soheil Kolouri, Praveen Pilly, James McClelland5545-5552

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate our method on learning two sets of sequential learning tasks: permuted MNIST tasks and digit recognition tasks. These are standard benchmark classification tasks for sequential task learning. We adjust them for our learning setting. Each class in these tasks is considered to be a concept, and each task of the sequence is considered to be learning the concepts in a new domain.
Researcher Affiliation Collaboration Mohammad Rostami University of Pennsylvania mrostami@seas.upenn.edu Soheil Kolouri HRL Laboratories, LLC skolouri@hrl.com James Mc Clelland Stanford University jlmcc@stanford.edu Praveen Pilly HRL Laboratories, LLC pkpilly@hrl.com
Pseudocode Yes Algorithm 1 ECLA (L, λ, η)
Open Source Code No The paper does not provide any explicit statement about open-sourcing the code or a link to a code repository.
Open Datasets Yes We validate our method on learning two sets of sequential learning tasks: permuted MNIST tasks and digit recognition tasks. These are standard benchmark classification tasks for sequential task learning. ... We performed a second set of experiments on a more realistic scenario. We consider two handwritten digit recognition datasets for this purpose: MNIST (M) and USPS (U) datasets. USPS dataset is a more challenging classification task as the size of the training set is smaller (20,000 compared to 60,000 images).
Dataset Splits No The paper mentions 'standard testing split' but does not provide specific percentages or counts for training, validation, or test splits. It does not mention a validation split.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch, TensorFlow, or scikit-learn with their respective versions).
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or specific optimizer settings.