Category: Machine Learning Basics
-
Where is the data stored in a trained ML model?
The final trained model doesn’t store the actual training data, but rather extracts patterns, relationships, and representations from it during training. How much of the training data is “stored” in a model depends on the type of model and how it’s designed, but here’s a general breakdown: Classical Machine Learning Models (e.g., Decision Trees, SVMs):…
-
Addressing Data Imbalance using GCP Native Tools
Sure! Here’s the content formatted as HTML: “`html GCP Tools for Handling Imbalanced Datasets GCP Tools for Handling Imbalanced Datasets in ML 1. AI Platform (Vertex AI) Custom Model Training: Vertex AI supports training with custom code, enabling you to implement techniques like oversampling, undersampling, or class weighting. Hyperparameter Tuning: You can tune parameters such…
-
F1 Score in Machine Learning
Understanding the F1 Score in Machine Learning The F1 score is a measure of a model’s accuracy that takes both precision and recall into account. It is the harmonic mean of precision and recall, giving a balanced view of the performance, especially for binary classification tasks. Precision and Recall Precision is the proportion of…
-
Machine Learning – Labeling Best Practices
Creating labels for a machine learning dataset is a critical step, especially for supervised learning tasks where models need to learn from **labeled** examples. Here’s how you can approach creating labels for different types of machine learning datasets: ### **Steps for Creating Labels** #### 1. **Understand the Problem Domain** – Before creating labels, you need…
-
Labeling vs Predictions in ML
In Machine Learning (ML), **labeling** and **prediction** refer to different stages in the machine learning workflow: 1. **Labeling**: – **Definition**: Labeling is the process of assigning correct or known output values (called labels) to data points. These labels are used during the training phase of supervised learning models. For example, in an image classification task,…
-
Machine Learning Model Parameters and Memory Usage
The **parameters** in a machine learning (ML) model directly affect the **memory usage** because they determine the amount of data the model needs to store and process during training and inference. The more parameters a model has, the more memory it consumes. Here’s a breakdown of how this works: ### 1. **Memory for Storing Parameters**…
-
Are parameters known prior to Training an ML Model?
### Are Parameters Known Prior to Training an ML Model? The process of determining the parameters of a model is known as **training**. During training, the model learns from the data by iteratively adjusting its parameters to optimize a given objective function (also known as a loss function). So – No, **parameters are not known…
-
Principal Component Analysis (PCA) versus Feature Crossing
Feature crossing and Principal Component Analysis (PCA) are both techniques used in machine learning to manipulate features, but they serve different purposes and operate differently. Feature Crossing Feature crossing involves creating new features by combining existing ones. This technique is particularly useful in linear models, where interactions between features can help the model capture more…
-
Real Time Object Detection Algorithms
YOLO provides real time object detection. Logistic Regression, Naive Bayes and SVC are not for Computer vision, but for conventional Machine Learning. Need a hands-on Data Architect, AI, ML or GCP Consultant? Need help with your data journey? Start the conversation today.
-
Reduce Dimensionality of Data using PCA
Reducing the number of Dimensions is a common step for pre-processing data. This enables us to overcome the downsides of dimensionality. Principal Component Analysis – PCA is a technique for achieving this but it works only on numerical data. Need a hands-on Data Architect, AI, ML or GCP Consultant? Need help with your data journey?…