Mengliu ZhaoinTowards Data ScienceA Patch is More than 16*16 PixelsOn Pixel Transformer and Ultra-long Sequence Distributed Transformer7 min read·3 days ago--
Cristian LeoinTowards Data ScienceThe Math Behind KAN — Kolmogorov-Arnold NetworksA new alternative to the classic Multi-Layer Perceptron is out. Why is it more accurate and interpretable? Math and Code Deep Dive.13 min read·Jun 12, 2024--8
Giuseppe ScalamognainTowards Data ScienceFrom Prompt Engineering to Agent EngineeringIntroducing a Practical Agent Engineering Framework9 min read·May 29, 2024--5--5
LucianoSphere (Luciano Abriata, PhD)inTowards Data Science“Sparks of Chemical Intuition”—and Gross Limitations!—in AlphaFold 3Observations after 3 weeks of DeepMind releasing its hitherto most advanced model for biomolecular structure prediction.·16 min read·Jun 5, 2024----
Jonte DanckerinTowards Data ScienceN-HiTS — Making Deep Learning for Time Series Forecasting More EfficientA deep dive into how N-HiTS works and how you can use it·10 min read·May 30, 2024--1--1
Mengliu ZhaoinTowards Data ScienceA Patch is More than 16*16 PixelsOn Pixel Transformer and Ultra-long Sequence Distributed Transformer7 min read·3 days ago--
Cristian LeoinTowards Data ScienceThe Math Behind KAN — Kolmogorov-Arnold NetworksA new alternative to the classic Multi-Layer Perceptron is out. Why is it more accurate and interpretable? Math and Code Deep Dive.13 min read·Jun 12, 2024--8
Giuseppe ScalamognainTowards Data ScienceFrom Prompt Engineering to Agent EngineeringIntroducing a Practical Agent Engineering Framework9 min read·May 29, 2024--5
LucianoSphere (Luciano Abriata, PhD)inTowards Data Science“Sparks of Chemical Intuition”—and Gross Limitations!—in AlphaFold 3Observations after 3 weeks of DeepMind releasing its hitherto most advanced model for biomolecular structure prediction.·16 min read·Jun 5, 2024--
Jonte DanckerinTowards Data ScienceN-HiTS — Making Deep Learning for Time Series Forecasting More EfficientA deep dive into how N-HiTS works and how you can use it·10 min read·May 30, 2024--1
Yann-Aël Le BorgneinTowards Data ScienceOpenAI vs Open-Source Multilingual Embedding ModelsChoosing the model that works best for your data12 min read·Feb 24, 2024--14
Matthew GuntoninTowards Data ScienceUnderstanding You Only Cache OnceThis blog post will go in detail on the “You Only Cache Once: Decoder-Decoder Architectures for Language Models” Paper and its findings9 min read·Jun 4, 2024--
Vyacheslav EfimovinTowards Data ScienceReinforcement Learning, Part 3: Monte Carlo MethodsFrom casinos to AI: unveiling the power of Monte Carlo methods in complex environments12 min read·May 23, 2024--