Tutorial for M1, M1 Pro, M1 Max and M2 — If you are a Data Scientist, Data Analyst, Researcher, or enthusiastic in these fields of knowledge, you certainly have heard about or read somewhere about how the recent ARM processors from Apple can boost your work. I recently bought a MacBook Pro 14 with an M1 Pro processor and I…

Understanding Loss Functions in Machine Learning — Table of contents: What is a loss function? Loss Functions vs Metrics Why are loss functions applied while building the model? Regression: Mean Squared Error (MSE) Mean Absolute Error (MAE) Root Mean Squared Error (RMSE) Mean Bias Error (MBE) Huber Loss Binary Classification: Binary Cross Entropy (BCE) Hing Loss and Squared Hing…

With Python code — What are outliers? Outliers are data values located too much distance from the other data values. Data outliers can occur naturally or be because of inaccurate measures, typo errors, or system malfunction. Similar to missing values, outliers undermine data science projects and return wrong results or predictions. …

Starting from Health Tech background — Since 2012, when Harvard Business Review declared Data Scientist as the sexiest job of the 21st century, getting a job in Data Science seems to be the Holy Grail of many graduates from Computer Science, Maths, IT, Statistics, and other STEM degrees. …

Using Keras and TensorFlow — Densenet is the last architecture we will explore in this series of articles about convolutional networks and image classification. If you already have some knowledge about classic Machine Learning, you can start here, and read all articles in the same order they were published. …

The giant leap in efficiency and performance — In previous articles, we learned about Inception modules and Residual Networks, and how these architectures helped to improve model efficiency and performance. This article is about Xception, a convolutional model that combines the architectures of Inception and ResNet. Xception is a model first proposed in 2016 by François Chollet in…

All price ranges as of September 2023 — The last time I bought a pair of headphones we were still in a pre-pandemic world, was 2018! At that time I opted for the Sony WH-1000XM3 and Audio-Technica ATH-SR6BT. At this point, I already had a Shure SRH440 with cable. …

As always, using Keras and Tensorflow! — In the last article, we learned about Residual Connections and their importance in neural networks to prevent gradient vanishing. In this article we we will learn how to build a Residual module and how to implement a full convolutional neural network with residual connections, as well as to compare the…

The problem of vanishing gradient — Residual connections were introduced in 2016 with the paper “Deep Residual Learning for Image Recognition” published by He, Zhang, Ren, and Sun at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Residual connections facilitate a smooth gradient flow during training, improving the vanishing gradient problem. …