Javier – Medium

Javier

How can Transformers handle variable length input?

Exposing one of the most untapped properties of self-attention

4 min readMar 3, 2024

--

1

How can Transformers handle variable length input?

--

1

Javier

Insights from a Senior AI Research Engineer

Self reflected learnings with examples from my experience

11 min readMay 29, 2023

--

Insights from a Senior AI Research Engineer

--

Javier

PyTorch BatchNorm2D Weights Explained

Understanding PyTorch BatchNorm2D and its weights

3 min readJul 17, 2022

--

PyTorch BatchNorm2D Weights Explained

--

Javier
in
Towards Data Science

Pytorch Conv2d Weights Explained

Understanding weights dimension, visualization, number of parameters and the infamous size mismatch

5 min readNov 26, 2021

--

1

Pytorch Conv2d Weights Explained

--

1

Javier
in
Towards Data Science

Human Priors in Object Detection

What we tell the AI determines how it learns

8 min readMar 9, 2021

--

Human Priors in Object Detection

--

Javier
in
Towards Data Science

TensorFlow 2.1: A How-To

The keras mode, the eager mode and the graph mode

8 min readApr 19, 2020

--

1

TensorFlow 2.1: A How-To

--

1

Javier
in
Towards Data Science

Keras Custom Training Loop

How to build a custom training loop in Keras at a lower level of abstraction, K.function, get_updates usage and other stuff under the hood

9 min readOct 19, 2019

--

3

Keras Custom Training Loop

--

3

Javier

How to write a linux device driver

A beautiful guide for the Hello World of the device driver programming

6 min readAug 20, 2017

--

4

How to write a linux device driver

--

4

Javier

Javier

AI Research Engineer in Deep Learning. Living between the math and the code. A philosophic seeker interested in the meaning of everything from quarks to AI.

Following

Help
Status
About
Careers
Blog
Privacy
Terms
Text to speech
Teams