Sweta Patra
Software Engineer by profession,Technology Enthusiast at heart.
Pune, India
Actions
I am an ardent technology enthusiast, constantly seeking knowledge about the latest advancements in AI, ML, NLP, and Data Science. These cutting-edge technologies have the potential to revolutionise industries and shape the future. Exploring their endless possibilities and applications is a never-ending journey that I wholeheartedly embrace.
I'm always eager to engage in meaningful conversations, explore new opportunities, and connect with fellow professionals who share my enthusiasm.
Area of Expertise
Topics
Pre-training vs. Fine-tuning in Transformers: What Works Best?
This talk will explore the interplay between **pre-training** large-scale Transformer models on general corpora and the subsequent **fine-tuning** on domain-specific tasks to achieve state-of-the-art performance. We will examine the trade-offs between these two stages, focusing on challenges such as overfitting, computational demands, and maintaining model generalization. Through empirical results from legal text analysis, we will demonstrate how fine-tuning can significantly enhance model performance, particularly when combined with strategies like data augmentation and retraining on incorrect predictions. Attendees will gain a deeper understanding of how to effectively leverage pre-training and fine-tuning for specialized tasks, optimizing performance while addressing practical challenges in real-world applications.
Pre-training vs. Fine-tuning in Transformers: What Works Best?
In the realm of Natural Language Processing (NLP), Transformers have become the dominant architecture, with pre-training and fine-tuning playing pivotal roles in their success. This talk will explore the interplay between **pre-training** large-scale Transformer models on general corpora and the subsequent **fine-tuning** on domain-specific tasks to achieve state-of-the-art performance. We will examine the trade-offs between these two stages, focusing on challenges such as overfitting, computational demands, and maintaining model generalization. Through empirical results from legal text analysis, we will demonstrate how fine-tuning can significantly enhance model performance, particularly when combined with strategies like data augmentation and retraining on incorrect predictions. Attendees will gain a deeper understanding of how to effectively leverage pre-training and fine-tuning for specialized tasks, optimizing performance while addressing practical challenges in real-world applications.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top