A detailed review of the book 'Deep Learning with PyTorch,' covering its structure, content, and suitability for students and practitioners.
A podcast transcript discussing the importance of writing for career growth in tech, covering motivation, process, and Amazon's writing culture.
A technical deep dive into real-time machine learning for recommendation systems, comparing approaches in China and the US and discussing implementation.
Explores the connection between machine learning and statistics by building a statistical inference model from a neural network example.
A data scientist's 2020 review, focusing on machine learning projects for healthcare, including mining COVID-19 EHR data and brain signal analysis.
A data scientist's 2020 reflection on moving to Amazon, building ML systems, and establishing a weekly writing habit for learning and sharing knowledge.
Explores the difference between inference and prediction in data modeling, using a Click Through Rate (CTR) example to contrast Machine Learning and Statistics.
Analyzes the fallout from Timnit Gebru's firing from Google and debates appropriate community responses in the AI research field.
Analyzes three experiments on the ICML 2020 peer-review process, focusing on resubmission bias, discussion effects, and reviewer recruiting.
An interview with lead data scientist Alexey Grigorev on his career transition from software engineering to data science, his advice, and his work at OLX.
Explains the Neural Tangent Kernel concept through simple 1D regression examples to illustrate how neural networks evolve during training.
A tutorial on building a serverless question-answering API using BERT, Hugging Face, AWS Lambda, and EFS to overcome dependency and model load limitations.
Explains the concept of causally correct partial models for reinforcement learning in POMDPs, focusing on counterfactual policy evaluation.
The article argues that the choice of machine learning library (like PyTorch or TensorFlow) is less critical than building robust data and production pipelines.
Explains the differences between Applied Scientist, Research Scientist, and ML Engineer roles in data science and machine learning.
Introducing efsync, an open-source MLOps toolkit for syncing dependencies and model files to AWS EFS for serverless machine learning.
An interview with Chip Huyen about her journey from a small village to Stanford and a career in ML, her writing, and thoughts on machine learning in production.
An analysis of GPT-3's capabilities, potential for misuse in generating fake news and spam, and its exclusive licensing by Microsoft.
Explains the theory behind linear regression models, a fundamental machine learning technique for predicting continuous numerical values.
Discusses the pitfalls of overengineering machine learning models for business, contrasting Kaggle's optimization goals with real-world value creation.
