Search Results for author:
Found 10 papers, 3 papers with code
Mixture of Experts Meets Prompt-Based Continual Learning
Exploiting the power of pre-trained models, prompt-based approaches stand out compared to other continual learning solutions in effectively preventing catastrophic forgetting, even with very few learnable parameters and without the need for a memory buffer.
Efficacy of Neural Prediction-Based Zero-Shot NAS
In contrast, handcrafted performance indicators (zero-shot NAS), which use the same architecture with random initialization, can generalize across multiple search spaces.
Ranked #38 on
Neural Architecture Search
on CIFAR-10
Revisiting Edge Detection in Convolutional Neural Networks
The ability to detect edges is a fundamental attribute necessary to truly capture visual concepts.
Robust Deep Neural Networks Inspired by Fuzzy Logic
Deep neural networks have achieved impressive performance and become the de-facto standard in many tasks.
A Deep Dive into Word Sense Disambiguation with LSTM
LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD).
Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?
Recently, Yuan et al. (2016) have shown the effectiveness of using Long Short-Term Memory (LSTM) for performing Word Sense Disambiguation (WSD).
A Critique of a Critique of Word Similarity Datasets: Sanity Check or Unnecessary Confusion?
Critical evaluation of word similarity datasets is very important for computational lexical semantics.
Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
Error propagation is a common problem in NLP.
