The Association of Data Scientists (AdaSci), the premier global professional body of data science and ML practitioners, has announced a hands-on workshop on meta-learning on March 13, Saturday.
The unavailability of large datasets has turned out to be a huge problem in solving critical challenges with machine learning and artificial intelligence. As a matter of fact, deep learning’s progress often gets impeded due to the unavailability of adequate labelled data.
In many cases, it becomes challenging to collect a sufficiently large number of labelled data, which inspired many research efforts on exploring ways to train robust models for various learning tasks beyond labelled data. Further, to train complex deep learning algorithms and models need high computational power.
In this workshop, the attendees get to learn about meta-learning — a subfield of machine learning where deep learning models are trained with fewer data efficiently. Known as ‘learning how to learn,’ meta-learning is an exciting trend in machine learning.
The full-day workshop on meta-learning will introduce topics such as few-shot learning; deep multi-task learning; parameter-level approach; zero-shot, one-shot and low-shot learning and more. The workshop will also discuss the implementation of different few-shot learning networks with PyTorch and TensorFlow, including siamese; matching; prototypical; relational; and memory augmented networks.
Additionally, the workshop will allow a hands-on implementation of meta-learning methods with PyTorch and TensorFlow, including model agnostic meta-learning; meta-SGD; open AI’s reptile; domain adaptive meta-learning; LSTM meta-learner; task-agnostic meta-learning and more. Attendees will also gain a comprehensive understanding of the applications of meta-learning in the healthcare sector, robotics, chatbots, fake news, and self-driving vehicles.
The participants should have a basic to moderate level understanding of Python, as well as basic knowledge of Pandas, Numpy, Scikit-Learn, TensorFlow, PyTorch and Keras. The workshop would also expect the attendees to have a nodding acquaintance with deep learning, convolutional neural network and recurrent neural network, and familiarity with Google Colab and GPU environment.
Attendees also need to have a few tools like an editor to run the python programs, preferably Google Colab Notebooks and install Pandas, NumPy, Scikit-learn, TensorFlow, PyTorch and Keras. A high-speed internet connection is mandatory.
Upon completing the workshop, the attendees will gain hands-on experience in meta-learning and few-shot learning and their applications in AI and ML. They will learn about the latest advancement in meta-learning and be equipped to kickstart image classification using meta-learning. Attendees will also get a certificate on hands-on meta-learning with Python.
Details of the workshop:
Date: March 13, 2021
Timings (Full day): 10:00 am to 5:00 pm (IST)
Pricing: $12.99 (workshop is free for ADaSci members)