Skip to content

Home

Welcome to my digital diary, where numbers dance, and algorithms whisper the secrets of the universe. Here, we take a delightfully unserious approach to very serious topics like data science and machine learning, or, Goddamnit AI!

The human brain might be the universe's most complex enigma. Crack its code, and you could unlock the cosmos itself.

Dive into Learning from Data - MNIST Video Adventure

MNIST MinMax and PCA restored

Hey there, data enthusiasts! Today, we're diving into the fascinating world of Machine Learning Classification using one of the most iconic datasets out there - the MNIST dataset. MNIST stands for Modified National Institute of Standards and Technology.

We're diving into the realm of MNIST - a dataset that's like a treasure map for budding data scientists. It contains thousands of handwritten digits from 0 to 9. Each image is a snapshot of someone's attempt to scribble a number, and our mission is to make sense of these scribbles.

Matrix Multiplication and Broadcasting - The Heartbeat of Data Transformations

Understanding the transformation of input through weights and biases is fundamental in machine learning. Let's dive into how matrix multiplication plays a crucial role. It's all about matrix multiplication, the bread and butter of transforming inputs into meaningful outputs. Let's dive into how weights, biases, and inputs dance together in this mathematical ballet.

matrix multiplication

For matrix multiplication, the number of columns in the first matrix must be equal to the number of rows in the second matrix. The result matrix has the number of rows of the first and the number of columns of the second matrix.

Text-to-Speech (TTS) Models Overview, Little Theory and Math

Audio is a very complicated data structure, just take a look for a 1 sec waveform...

audio-animation
Audio exhibits patterns at multiple time scales. Source: Google DeepMind.

Developing a high-quality text-to-speech (TTS) system is a complex task that requires extensive training of machine learning models. While successful TTS models can revolutionize how we interact with technology, enabling natural-sounding speech synthesis for various applications, the path to achieving such models is often paved with challenges and setbacks.