-
🤔 How to pick the right #GoogleCloud #MachineLearning tool for your application?
Answer these questions
-
❓ What's your teams ML expertise?\
-
❓ How much control/abstraction do you need?
-
❓ Would you like to handle the infrastructure components?
-
🔹 ML APIs → goo.gle/2r30flz
-
🔹 AutoML → goo.gle/38zZS2E
-
🔹 BQML → goo.gle/2PwbgVX
-
🔹 AI Platform → goo.gle/36JYPLW
-
🔹 Kubeflow → goo.gle/2PvJRDk
-
🔹 Deep Learning VMs → goo.gle/2rYttST
-
🔹 Tensorflow → goo.gle/35zholN
This pyramid helps explain the idea. As you move up the pyramid, less ML expertise is required, and you also don’t need to worry as much about the infrastructure behind your model.
Checkout this video by Sara Robinson 👉 https://lnkd.in/gX5DBCh If Twitter is your thing then checkout the entire thread 👉 https://lnkd.in/gunaCFK
-
-
https://www.linkedin.com/posts/rodneymunoz_what-is-bigqueryml-activity-6768513005979242496-YieH
Today I played with BigQueryML. Here's what I learned:
- ✅ Lets you create & execute #MachineLearning models in BigQuery
- ✅ If you know SQL no need to learn anything new to create ML models
- ✅ Increases development speed by eliminating the need to move data
Models supported by BigQuery ML
- 🔹 Linear regression for forecasting
- 🔹 Binary & multiclass logistic regression for classification
- 🔹 K-means clustering for data segmentation
- 🔹 Matrix Factorization for creating recommendation systems
- 🔹 Time series for performing forecasts
- 🔹 Boosted Tree for creating XGBoost based classification and regression models.
- 🔹 Deep Neural Network for creating TensorFlow based DNNs for classification & regression
- 🔹 AutoML Tables
- 🔹 TensorFlow model importing
Steps to create binary logistic regression model
- 1️⃣ CREATE MODEL statement
- 2️⃣ ML.EVALUATE function to evaluate the ML model
- 3️⃣ ML.PREDICT function to make predictions using the ML model