Skip to main content

Extension

Instruction and application
Complete

Why keep learning?​

Illustration

The world of AI is constantly evolving.

The ongoing emergence of novel architectures, optimisation strategies, and hardware advancements presents significant opportunities for enhanced model performance, efficiency gains, and the development of more sustainable AI practices.

By actively engaging with these evolving concepts, you can refine your skills, implement state-of-the-art techniques, and ultimately drive more impactful and innovative solutions within your organisation.

Dive deeper: Additional learning materials​

If you're interested, use the following resources to continue exploring topics related to this unit.

  • Comprehensive documentation and tutorials covering various aspects of machine learning model building and training using the TensorFlow framework. Includes guides on model architectures (like neural networks), training techniques, optimization, and deployment.
  • A wide range of tutorials for learning PyTorch, another popular deep learning framework. Covers fundamental concepts of tensor manipulation, model building, training loops, and advanced topics like transfer learning and distributed training.
  • Free, accessible courses on practical deep learning. Offers a top-down approach, emphasizing building and training models early on. Covers various model architectures and training techniques with a focus on achieving state-of-the-art results.
  • A platform that aggregates machine learning papers, code implementations, and leaderboards. Useful for staying up-to-date with the latest research in model architectures, training techniques, and performance benchmarks across different tasks.
  • Features articles and research updates from Google's AI division, often covering advancements in model architectures, training methodologies, and the computational infrastructure used for large-scale ML.
  • Documentation for the Transformers library, a key resource for working with pre-trained language models and implementing transfer learning techniques in Natural Language Processing.
  • A series of in-depth courses taught by Andrew Ng covering the fundamentals of deep learning, including neural network architectures, training algorithms, and practical implementation.
  • Contains articles and insights on various aspects of machine learning experimentation, including hyperparameter tuning, model evaluation, and best practices for training and deploying models.
  • Provides benchmarks for measuring the performance of machine learning hardware and software. Useful for understanding the computational and operational considerations of training models on different infrastructure.