Angel Igareta – Medium

Pinned

Angel Igareta
in
Towards Data Science

The Million-Dollar Question: When to Stop Training your Deep Learning Model

On early stopping, or how to avoid overfitting or underfitting by knowing how long to train your neural network for

5 min readJun 22, 2021

--

1

The Million-Dollar Question: When to Stop Training your Deep Learning Model

--

1

Pinned

Angel Igareta
in
Towards Data Science

Dealing with Imbalanced Data in TensorFlow: Class Weights

Class imbalance is a common challenge when training Machine Learning models. Here is a possible solution by generating class weights and…

4 min readJun 8, 2021

--

2

Dealing with Imbalanced Data in TensorFlow: Class Weights

--

2

Angel Igareta
in
Klarna Engineering

Stop Misusing ROC Curve and GINI: Navigate Imbalanced Datasets with Confidence

Discover how the Precision-Recall curve can provide a more robust metric for binary classification in data science and machine learning.

9 min readNov 9, 2023

--

Stop Misusing ROC Curve and GINI: Navigate Imbalanced Datasets with Confidence

--

Angel Igareta
in
Towards Data Science

Taking the TensorBoard Embedding Projector to the Next Level

TensorBoard Projector allows to graphically represent low-dimensional embeddings. Here I show you how, instead of displaying a point, you…

4 min readJul 28, 2021

--

3

Taking the TensorBoard Embedding Projector to the Next Level

--

3

Angel Igareta
in
Towards Data Science

Stratified Sampling: You May Have Been Splitting Your Dataset All Wrong

Randomly generating splits of the data set is not always the optimal solution, as the proportions in the target variable can be extremely…

3 min readJul 21, 2021

--

1

Stratified Sampling: You May Have Been Splitting Your Dataset All Wrong

--

1

Angel Igareta
in
Towards Data Science

Removing Duplicate or Similar Images in Python

When training a machine learning model that uses images as input, it is relevant to check for similar or duplicated pictures in the…

3 min readJul 14, 2021

--

2

Removing Duplicate or Similar Images in Python

--

2

Angel Igareta
in
Towards Data Science

How to Split a Tensorflow Dataset into Train, Validation, and Test sets

4 min readJun 2, 2021

--

Person deciding which path to go to reach the destination. Reference to split data set in TensorFlow.

--

Angel Igareta
in
Towards Data Science

A better comparison of TensorBoard experiments

An existing TensorBoard limitation is that it only considers the last epoch when ranking experiments. Here is how to better evaluate…

4 min readMay 12, 2021

--

A better comparison of TensorBoard experiments

--

Angel Igareta

Angel Igareta

Passionate about digital innovation. My goal is to use the data being collected in different domains to create new solutions that have a real impact.

Following

Help
Status
About
Careers
Blog
Privacy
Terms
Text to speech
Teams