Multi-Task Learning Courses and Certifications

Yannic Kilcher

Gradient Surgery for Multi-Task Learning

Explore PCGrad, a technique addressing gradient conflicts in multi-task learning, enhancing efficiency and performance in supervised and reinforcement learning scenarios.

• YouTube
• 32 minutes
• On-Demand
• Free Online Course

Stanford Seminar - The Next Generation of Robot Learning

4 reviews

Exploring advanced robot learning techniques for generalization across tasks, environments, and platforms, addressing challenges and proposing innovative approaches to data utilization and algorithm design.

• YouTube
• 56 minutes
• On-Demand
• Free Online Course

Stanford Seminar 2022 - DeepMind's Perceiver and Perceiver IO: New Data Family Architecture

Exploring DeepMind's Perceiver architecture for flexible AI processing across diverse data types, offering domain-general solutions comparable to specialized models in various tasks.

• YouTube
• 59 minutes
• On-Demand
• Free Online Course

Stanford CS330: Deep Multi-Task and Meta Learning

Explore advanced machine learning techniques for efficient learning across multiple tasks, including optimization-based meta-learning, Bayesian approaches, and reinforcement learning applications.

• YouTube
• 18 hours
• On-Demand
• Free Online Course

Intuitions on Language Models and Shaping AI's Future - Stanford CS25 Lecture

Explore intuitions on language models and the evolution of Transformer architectures with OpenAI researchers. Gain insights into next-word prediction, scaling laws, and the future of AI development.

• YouTube
• 1 hour 17 minutes
• On-Demand
• Free Online Course

DeepLearning.AI;  Stanford

Structuring Machine Learning Projects

6 reviews

Learn to structure and optimize machine learning projects, diagnose errors, and make strategic decisions as an ML project leader to improve system performance and efficiency.

• Coursera
• 6 hours 37 minutes
• On-Demand
• Free Online Course (Audit)

Yannic Kilcher

IMPALA - Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

Explore IMPALA, a distributed reinforcement learning architecture for efficient multi-task learning. Learn about V-trace, off-policy correction, and scalable performance across thousands of machines.

• YouTube
• 21 minutes
• On-Demand
• Free Online Course

Graham Neubig

Neural Nets for NLP 2019: Sentence and Contextualized Word Representations

Explore sentence representations and contextual word embeddings for NLP tasks. Learn about multi-task learning, transfer learning, and pre-training techniques to improve model performance.

• YouTube
• 1 hour 18 minutes
• On-Demand
• Free Online Course

Graham Neubig

CMU Multilingual NLP 2020 - Advanced Text Classification-Labeling

Explore advanced text classification and sequence labeling methods, including subword models, unsupervised training, and structured prediction for multilingual NLP applications.

• YouTube
• 50 minutes
• On-Demand
• Free Online Course

Graham Neubig

CMU Neural Nets for NLP 2020 - Multitask and Multilingual Learning

Explore multitask and multilingual learning in NLP, covering methods, objectives, and challenges. Gain insights into cross-lingual transfer, data balancing, and zero-shot approaches.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Online Course

Graham Neubig

CMU Advanced NLP: Pre-training Methods

Explore advanced NLP concepts including multi-task learning, sentence embeddings, BERT variants, and language modeling objectives. Gain insights into cutting-edge techniques for natural language processing.

• YouTube
• 1 hour 22 minutes
• On-Demand
• Free Online Course

Graham Neubig

Advanced NLP: Adversarial Methods for Text

Explore advanced NLP techniques including adversarial networks, discrete outputs, and input manipulation for robust language models and applications.

• YouTube
• 1 hour 17 minutes
• On-Demand
• Free Online Course

Yannic Kilcher

Active Dendrites Avoid Catastrophic Forgetting - Interview With the Authors

Interview exploring how active dendrites in neural networks can mitigate catastrophic forgetting, enabling better multi-task and continual learning for AI systems in dynamic environments.

• YouTube
• 57 minutes
• On-Demand
• Free Online Course

Yannic Kilcher

Avoiding Catastrophe - Active Dendrites Enable Multi-Task Learning in Dynamic Environments

Explore how active dendrites in neural networks mitigate catastrophic forgetting, enabling multi-task learning and adaptation in dynamic environments through context-sensitive gating and sparse representations.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Online Course

Alexander Amini;  MIT

MIT 6.S191 - Deep Learning Limitations and New Frontiers

Explore deep learning limitations, adversarial attacks, uncertainty quantification, and AutoML in this lecture. Gain insights into neural network challenges and emerging frontiers in AI research.

• YouTube
• 36 minutes
• On-Demand
• Free Online Course