Learnings

<p>A Python framework for creating reproducible, maintainable and modular data science code: </p>

<p>Using AntiPatterns to avoid MLOps Mistakes: </p>

<p>Awesome Machine Learning FAQ </p>

<p>Extrapolating to Unnatural Language Processing with GPT-3's In-context Learning: The Good, the Bad, and the Mysterious </p>

<p>Overview of Consistency training on Deep Learning: contrastive learning, energy-based modelling, etc. </p>

<p>Hold-out validation vs. cross-validation: </p>

<p>Using a fixed training-development-test split in sklearn: </p>

<p>Nested Cross-Validation for Machine Learning with Python: </p>

<p>Using PyTorch + NumPy? You're making a mistake. </p>

<p>Tesla's Data Engine and what we should all learn from it: </p>

<p>Minimal tutorial on packing (pack_padded_sequence) and unpacking (pad_packed_sequence) sequences in pytorch: </p>

<p>Most Common Neural Net PyTorch Mistakes: </p>

<p>Understanding “Deep Double Descent”: bigger models are always better? </p>

<p>Why Deep Learning Works Even Though It Shouldn’t </p>

<p>Hierarchical Clustering and Dendrogram Tutorial: </p>

<p>Effective testing for machine learning systems: </p>

<p>"While researchers try to outdo one another on contrived benchmarks, one in every nine people in the world is starving" from Too many AI researchers think real-world problems are not relevant: </p>

<p>Data Science Meets Devops: MLOps with Jupyter, Git, &amp; Kubernetes </p>

<p>Create UIs for prototyping your machine learning model, compatible with Jupyter Notebooks: </p>

<p>Train sklearn 100x faster: </p>

<p>The New Business of AI (and How It’s Different From Traditional Software): </p>

<p>A gentle introduction to Visual Question Answering (VQA) using neural networks: </p>

<p>A Practical Guide to Feature Engineering in Python: </p>

<p>Cookiecutter Data Science: </p>