Search Results for author:
Found 10 papers, 2 papers with code
Learning Disentangled Audio Representations through Controlled Synthesis
This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning.
Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models.
Learning Disentangled Speech Representations
This benchmark dataset and framework address the gap in the rigorous evaluation of state-of-the-art disentangled speech representation learning methods.
Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
This study provides an empirical analysis of Barlow Twins (BT), an SSL technique inspired by theories of redundancy reduction in human perception.
Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI
They all have similar performance and they outperform transformers that are trained from scratch by a large margin.
Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks
Investigating deep learning language models has always been a significant research area due to the ``black box" nature of most advanced models.
Go with the Flow: the distribution of information processing in multi-path networks
The architectures of convolution neural networks (CNN) have a great impact on the predictive performance and efficiency of the model.
Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis
When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs.
Exploring the Properties and Evolution of Neural Network Eigenspaces during Training
In this work we explore the information processing inside neural networks using logistic regression probes \cite{probes} and the saturation metric \cite{featurespace_saturation}.
Size Matters
Fully convolutional neural networks can process input of arbitrary size by applying a combination of downsampling and pooling.
