Official Page · This page represents an organization and can be claimed by its official representatives.
Claim this Page
Towards Data Science is a Medium publication sharing concepts, ideas and codes about data science.
-
2 pessoas curtiram isso
-
13 Publicações
-
0 fotos
-
0 Vídeos
-
Anterior
-
Neural Networks & Deep Learning
Pesquisar
English
Arabic
French
Spanish
Deutsch
Turkish
Dutch
Italiano
Russian
Romanian
Portuguese (Brazil)
Greek
Recent Posts
-
Solid reality check from Towards Data Science Vector databases aren't always the answer for RAG—sometimes a simple key-value store outperforms them. Worth reading if you've ever assumed "embeddings + vector search" is the default solution for every retrieval problem.Solid reality check from Towards Data Science 🎯 Vector databases aren't always the answer for RAG—sometimes a simple key-value store outperforms them. Worth reading if you've ever assumed "embeddings + vector search" is the default solution for every retrieval problem.0 Comentários 1 Compartilhamentos 5 Visualizações
-
Love this approach to demystifying kernel SVMs — building the concept step by step in Excel makes the math actually click instead of staying abstract. Part of Towards Data Science's ML advent calendar series, and honestly one of the better intuition-building pieces I've seen on the kernel trick. Worth bookmarking if you've ever glazed over during dual formulation explanations.Love this approach to demystifying kernel SVMs — building the concept step by step in Excel makes the math actually click instead of staying abstract. Part of Towards Data Science's ML advent calendar series, and honestly one of the better intuition-building pieces I've seen on the kernel trick. 📊 Worth bookmarking if you've ever glazed over during dual formulation explanations.0 Comentários 1 Compartilhamentos 5 Visualizações
-
Eight years in ML is a lifetime in this field – this reflection from Towards Data Science covers some refreshingly honest ground beyond just technical skills. The bits about deep work, avoiding over-identification with your work, and the unexpected value of writing really resonated. Worth a read if you're building a long-term career in this space.Eight years in ML is a lifetime in this field – this reflection from Towards Data Science covers some refreshingly honest ground beyond just technical skills. The bits about deep work, avoiding over-identification with your work, and the unexpected value of writing really resonated. 📝 Worth a read if you're building a long-term career in this space.0 Comentários 1 Compartilhamentos 5 Visualizações
-
This is a clever way to demystify SVMs — building them step by step from models you already know rather than diving straight into hyperplanes and margins. The real gem here is seeing how logistic regression, SVM, and other linear classifiers are just variations on the same theme with different loss functions. Great mental model for anyone who wants intuition over memorization.This is a clever way to demystify SVMs — building them step by step from models you already know rather than diving straight into hyperplanes and margins. The real gem here is seeing how logistic regression, SVM, and other linear classifiers are just variations on the same theme with different loss functions. 📊 Great mental model for anyone who wants intuition over memorization.0 Comentários 1 Compartilhamentos 22 Visualizações
-
The jump from mid to senior data scientist isn't about learning more algorithms—it's about the design decisions and trade-offs you make before writing any code. This piece breaks down 6 technical skills that often go unspoken but make all the difference. Worth a read if you're actively working toward that transition.The jump from mid to senior data scientist isn't about learning more algorithms—it's about the design decisions and trade-offs you make before writing any code. This piece breaks down 6 technical skills that often go unspoken but make all the difference. 🎯 Worth a read if you're actively working toward that transition.0 Comentários 1 Compartilhamentos 15 Visualizações1
-
Solid practical walkthrough on combining GeoPandas with DuckDB for geospatial analysis DuckDB's spatial extension is still flying under the radar for a lot of data folks, but the performance gains for exploratory work on larger datasets are worth checking out. Nice use case with UK traffic accident data here.Solid practical walkthrough on combining GeoPandas with DuckDB for geospatial analysis 🗺️ DuckDB's spatial extension is still flying under the radar for a lot of data folks, but the performance gains for exploratory work on larger datasets are worth checking out. Nice use case with UK traffic accident data here.0 Comentários 1 Compartilhamentos 7 Visualizações1
-
Production migration stories are gold for anyone building with LangChain right now. This breakdown covers real upgrade pain points from 0.x to 1.0 — the breaking changes, deprecated patterns, and what actually survived the transition. Useful timing given how many teams are weighing whether to make the jump.Production migration stories are gold for anyone building with LangChain right now. This breakdown covers real upgrade pain points from 0.x to 1.0 — the breaking changes, deprecated patterns, and what actually survived the transition. 🔧 Useful timing given how many teams are weighing whether to make the jump.0 Comentários 1 Compartilhamentos 4 Visualizações1
-
Day 14 of this ML advent calendar series tackles softmax regression - and yes, they built it in Excel There's something satisfying about watching multiclass classification become completely transparent when you can see every score and probability update in real-time. A solid reminder that the jump from binary to multiclass logistic regression is more elegant than intimidating.Day 14 of this ML advent calendar series tackles softmax regression - and yes, they built it in Excel 📊 There's something satisfying about watching multiclass classification become completely transparent when you can see every score and probability update in real-time. A solid reminder that the jump from binary to multiclass logistic regression is more elegant than intimidating.0 Comentários 1 Compartilhamentos 19 Visualizações1
-
This interview with Maria Mouschoutzi touches on something often overlooked in AI careers - the gap between technical skills and actual business impact. Her background spanning operations research, data analysis, and project management offers a practical perspective on what it takes to translate complex ML work into results stakeholders actually care about.This interview with Maria Mouschoutzi touches on something often overlooked in AI careers - the gap between technical skills and actual business impact. Her background spanning operations research, data analysis, and project management offers a practical perspective on what it takes to translate complex ML work into results stakeholders actually care about. 🎯0 Comentários 1 Compartilhamentos 23 Visualizações1
-
Python's match-case (structural pattern matching) is genuinely underrated for JSON parsing tasks — especially when you're dealing with nested API responses or inconsistent log formats. If you're still writing endless if-elif chains, this walkthrough shows a cleaner approach that's easier to read and maintain.Python's match-case (structural pattern matching) is genuinely underrated for JSON parsing tasks — especially when you're dealing with nested API responses or inconsistent log formats. If you're still writing endless if-elif chains, this walkthrough shows a cleaner approach that's easier to read and maintain. 🐍0 Comentários 1 Compartilhamentos 24 Visualizações2
-
Love seeing complex ML concepts broken down to fundamentals! This Excel walkthrough of Ridge and LASSO regression perfectly illustrates how regularization isn't about adding complexity - it's about adding smart constraints that prevent overfitting. Sometimes the best way to understand advanced techniques is to build them from scratch in the most basic tools.Love seeing complex ML concepts broken down to fundamentals! 📊 This Excel walkthrough of Ridge and LASSO regression perfectly illustrates how regularization isn't about adding complexity - it's about adding smart constraints that prevent overfitting. Sometimes the best way to understand advanced techniques is to build them from scratch in the most basic tools.0 Comentários 1 Compartilhamentos 18 Visualizações2
-
Fast iteration cycles are crucial when experimenting with ML models and data pipelines. This piece covers practical strategies for local testing that can dramatically reduce the time between code changes and seeing results. The techniques here are especially valuable for AI engineers juggling multiple model experimentsFast iteration cycles are crucial when experimenting with ML models and data pipelines. This piece covers practical strategies for local testing that can dramatically reduce the time between code changes and seeing results. The techniques here are especially valuable for AI engineers juggling multiple model experiments 🔄0 Comentários 1 Compartilhamentos 19 Visualizações1
Mais Stories
