A waste classification method based on a multilayer hybrid convolution neural network

C Shi, C Tan, T Wang, L Wang - Applied Sciences, 2021 - mdpi.com
With the rapid development of deep learning technology, a variety of network models for
classification have been proposed, which is beneficial to the realization of intelligent waste …

A reliable and robust deep learning model for effective recyclable waste classification

MM Hossen, ME Majid, SBA Kashem… - IEEE …, 2024 - ieeexplore.ieee.org
In response to the growing waste problem caused by industrialization and modernization,
the need for an automated waste sorting and recycling system for sustainable waste …

Autofreeze: Automatically freezing model blocks to accelerate fine-tuning

Y Liu, S Agarwal, S Venkataraman - arxiv preprint arxiv:2102.01386, 2021 - arxiv.org
With the rapid adoption of machine learning (ML), a number of domains now use the
approach of fine tuning models which were pre-trained on a large corpus of data. However …

Language generation via combinatorial constraint satisfaction: A tree search enhanced Monte-Carlo approach

M Zhang, N Jiang, L Li, Y Xue - arxiv preprint arxiv:2011.12334, 2020 - arxiv.org
Generating natural language under complex constraints is a principled formulation towards
controllable text generation. We present a framework to allow specification of combinatorial …

An approximate sampler for energy-based models with divergence diagnostics

B Eikema, G Kruszewski, CR Dance… - … on Machine Learning …, 2022 - openreview.net
Energy-based models (EBMs) allow flexible specifications of probability distributions.
However, sampling from EBMs is non-trivial, usually requiring approximate techniques such …

Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs

B Eikema, G Kruszewski, H Elsahar… - arxiv preprint arxiv …, 2021 - arxiv.org
Energy-Based Models (EBMs) allow for extremely flexible specifications of probability
distributions. However, they do not provide a mechanism for obtaining exact samples from …

[PDF][PDF] Constraint Satisfaction Driven Natural Language Generation: A Tree Search Embedded MCMC Approach

M Zhang, N Jiang, L Li, Y Xue - … of the Conference on Empirical Methods …, 2020 - par.nsf.gov
We provide a general framework for the constrained natural language generation. In this
framework, sentences are generated by sampling from a probability distribution that is …