Sitemap - 2020 - TheSequence

🎉🎁 Edge#Recap2: key topics

🎄🎊 Edge#Recap1: key topics

🤝 The AI Consolidation Movement will Continue in 2021

🎲 Edge#50: Facebook's HiPlot and Polygames for Advanced Deep Learning Experimentation

🕑 Edge#49: An Intro to Time-Series Forecasting

💯 The AI Platform Startup Ecosystem is Getting Crowded

☝️ Edge#48: When More Data and Bigger Models can Hurt Performance

🥓 Edge#47: What are Energy-Based Models?

👾 The Monster C3.AI IPO 

Survey: What technologies will give you an edge in 2021?

📣 Edge#46: Pro-ML is the Architecture Powering Machine Learning at LinkedIn

➡️ Edge#45: Understanding Encoder-Decoder Architectures and Sequence-to-Sequence Learning

🙋🏻‍♂️Learning from ML practitioners

🎙 Chat with Justin Harris: "My vision is for people to be compensated for the data they provide while keeping models free to use"

🎮 Edge#44: DeepMind’s Agent57 Which Outperformed Humans in 57 Atari Games

❄️ Edge#43: Bidirectional Long-Short Term Memory Networks

🔛🔝Salesforce Einstein Brings AutoML Models to a Massive Scale

☕️ Edge#42: What’s New in AI: LinkedIn's Dagli

🍁 Edge#41: Long-Short Term Memory Networks

ℹ️🅿️🌀 The First AI Startups IPOs

📏 Edge#40: On the Measure of Intelligence

🤯 Edge#39: Memory in Deep Learning Architectures

☕️ 🕸 Deep Learning for Java and .NET Developers

🧐 Edge#38: Uber Ludwig 0.3

📊 Edge#37: What is Model Drift?

⚡️ Keeping Up with AI Research and Technology

⛓ Edge#36: Blockchains, Smart Contracts and Incentives in Decentralized ML

🥦 Edge#35: What is Decentralized AI?

Decentralized AI: Myth or Reality?

🔏 Edge#34: Homomorphic Encryption

💰 Edge#33: The millionaire’s problem and sMPC

🚀 Synthetic Data in ML Models is Becoming Real

🤼 Edge#32: Adversarial Attacks

🔊 Edge#31: Differential Privacy

🗝🚪The Friction Between Privacy and Learning

🔐 Edge#30: Privacy-preserving machine learning

📚 Edge#29: Active Learning

☁️ A Heroku for Machine Learning

🐞 Edge#28: Debugging Machine Learning Models

⚫️ Edge#27: Contrastive learning and a list of Uber’s open-sourced ML contributions

Building Machine Learning with Machine Learning: Myth or Reality?

👶 Edge#26: Self-supervised learning; a method for image classification by Facebook; and Google’s SimCLR framework

🗂 Edge#25: Representation Learning, a practical representation learning method by Microsoft, and Facebook's fastText~

The Microsoft AI Powerhouse

📗 Edge#24: Text Summarization, Google’s PEGASUS; and Stanford’s CoreNLP in Java

📕 Edge#23: Machine Reading Comprehension, SQuAD 2.0 from Stanford University; and the spaCy framework

🧠 AI Inspired by Neuroscience

📖 Edge#22: Machine Text Generation; 17 billion parameters in Microsoft’s Turing-NLG; and the AllenNLP framework~

💬 Edge#21: Question-answering models; 300,000 natural questions in the new dataset; and the DeepPavlov framework~

📐 Size Matters 

🔂 Edge#20: What is MLOps, top MLOps technologies and Google’s TensorFlow Extended explained~

📈 Edge#19: Graph Neural Networks, combinatorial generalization as a top priority for AI, and the deep graph library~

🔷 End-to-End vs. Best-Of-Breed Machine Learning Platforms~

🗒 Edge#18: Production-ready notebooks, challenges with computational notebooks, and Polynote by Netflix~

🔲 Edge#17: Bayesian Neural Networks, how to assess the fairness of a dataset, and Pyro by Uber~

🔶 The Difficult Economics of AI Companies

🔳 Edge#16: Probabilistic Programming, ideas behind MIT’s Gen, and the three most popular PPLs~

👥 Edge#15: Machine Teaching; Uber's Generative Teaching Networks; and Snorkel-Flow~

➿ Does Machine Learning Requires Interoperability?

✨ Edge#14: The magic of semi-supervised learning~

The Introductory Post

⚖️ Edge#13: Interpretability vs Accuracy

🔥 Quantum Machine Learning is Becoming Real

🌀Edge#12: The challenges of Model Serving~

🍩 Edge#11: The Universe of Meta-Learning~

🚀 The Emerging Market of Data Labeling  

🏆 Edge#10: Feature Selection and Feature Extraction

Edge#9: Come across Parallel Training

TheSequence Scope: Can Machine Learning Write Better Machine Learning?

TheSequence Edge#8: GANs – two networks that learn by competing against each other

TheSequence Edge#7: The Generative Models

TheSequence Scope: The Challenge of Data-Efficient Machine Learning

The Sequence Edge#6: Diving Deep into Mobile Deep Learning

The Sequence Edge#5: A practical look into Federated Learning

TheSequence Scope: The Mismatch Between Machine Learning Research and Implementation

Edge#4: Beauty of Neural Architecture Search, and Uber's Ludwig that needs no code

Edge#3: Attention that Transformed Machine Learning

TheSequence Scope: Announcing The Sequence of AI Knowledge

Edge#2: AutoML, AutoML-Zero and the spell of TransmogrifAI

Edge #1: Hyperparameters, The Lottery Ticket Hypothesis, and Weight&Biases platform

TheSequence Scope: Architectures for Building AI at Scale

TheSequence Scope: Systematic AI Education

TheSequence Scope: Bridging the Gap Between Language and Vision in AI Systems

TheSequence Scope: OpenAI Launches its First Product

TheSequence Scope: Is Reinforcement Learning Ready for Prime Time

TheSequence Scope: The Transformer Race

TheSequence Scope: Microsoft's AI Week

TheSequence Scope: Reimagining Enterprise Search with Machine Learning

TheSequence Scope: Self-Supervised vs. Supervised vs. Reinforcement Learning

TheSequence Scope: Faster, Smaller Machine Learning

TheSequence Scope: PyTorch 1.5 is Here

TheSequence Scope: Visualizing Neural Networks

TheSequence Scope: The Biggest Roadblock for the Mainstream Adoption of Machine Learning