Unlocking Deep Learning fundamentals with PyTorch
Abhiram Ravikumar (~abhiram89) |
3
Description:
Dive into the world of deep learning with PyTorch! This session, inspired by Sebastian Raschka's workshop, will introduce the core concepts of PyTorch, empowering attendees to train neural networks for various tasks. Ideal for beginners, yet rich with insights for experienced folk too.
Tasks include:
- Image Classification: I will demo how to train a convolutional neural network (CNN) to recognize and classify images from common datasets like CIFAR-10 or MNIST. This example can showcase fundamental deep learning techniques and the ease of implementing them using PyTorch.
- Natural Language Processing (NLP): I will explain the basics of processing text using recurrent neural networks (RNNs) or transformers. A practical task could involve sentiment analysis on movie reviews or classifying spam vs. non-spam messages, highlighting how PyTorch handles sequential data.
Outline
Introduction to PyTorch (5 mins): Understanding the PyTorch ecosystem and its advantages.
Tensors and Automatic Differentiation (5 mins): The building blocks of PyTorch.
Building Neural Networks (10 mins): Step-by-step guide to creating, training, and evaluating models.
Case Study: Image Classification (5 mins): Real-world application in image classification.
Q&A (5 mins): Addressing questions and discussing additional resources.
Who is the talk for?
This talk is designed for Python programmers new to PyTorch and deep learning. It's also beneficial for experienced deep learning practitioners looking to deepen their understanding of PyTorch and explore new tools and techniques.
Key Takeaways
A solid understanding of PyTorch fundamentals.
Hands-on experience in building and training neural networks.
Practical knowledge of utilizing free GPU resources for deep learning.
Prerequisites
Basic knowledge of Python programming.
Familiarity with basic machine learning concepts is helpful but not required.
Prerequisites:
Basic knowledge of Python programming. Familiarity with basic machine learning concepts is helpful but not required.
Content URLs:
Speaker Info:
Abhiram is a Senior Data Scientist at Ai Palette. He holds a Master's degree in Data Science from King's College, London, and has an extensive background in natural language processing, quantum computing, brain-computer interfaces, and AI. A seasoned speaker and member of the Mozilla Tech Speakers program, Abhiram has presented at international tech conferences like PyCon, MozFest, and CodeMash, and his LinkedIn Learning course on Rust programming has reached over 60,000 participants.
Abhiram has a rich history in both academia and industry. He has published papers and posters at IEEE and ACM research conferences, and prior to his current role, he spent over four years as a developer and research fellow at SAP Labs in Bengaluru, where he specialized in web development, computer vision, and robotic process automation (RPA).
With practical experience in developing, testing, and deploying NLP products, including the application of the BERTopic topic modelling technique, Abhiram is well-positioned to provide deep insights into the changing landscape of topic modelling due to Large Language Models. His recent talk at the Analytics Vidhya DataHour Forum Talk series on clustering topic models, attended by over 4,200 participants, received an impressive feedback rating of 4.6/5, underscoring his ability to effectively communicate complex topics to diverse audiences.
Speaker Links:
Events and speaking engagements
- AngelHack talk on RAG based chatbots
- Conf42 talk on BERT Model
- Analytics Vidhya session on BERTopic clustering
- PyCon India 2018 - talk on Rust
Online presence
- LinkedIn - professional career
- GitHub - code base & projects
- Slides.com
- Speakerdeck.com - presentations and decks
- Twitter - @abhi12ravi