Machine Learning

A common pattern we have observed is that building and deploying a production-purpose ML model are done by different teams, typically an ML algorithm team and a device operation team. The ML team handles model training and evaluation, while the device team is responsible for migrating the model to the…

It took a 6th grade science fair for me to train my first neural network in a long while. My family lives in rural patch of Northern California filled with oak, redwood and other native flora. For the upcoming science fair my son decided to build a machine learning model…

Vectors — The Machine Learning Perspective Vectors are commonly used in machine learning as they lend a convenient way to organise data. There’s almost no ML model where vectors aren’t used at some point in the project lifecycle. Often one of the very first steps in making a machine learning model is vectorizing the data. What is a Vector ? Physics…

Hyperparameter tuning is a key step in model selection. Hyperparameters are like settings, if you do not handle them appropriately, it can have a bad impact on the results of the model. Tuning can be done manually or automatically. In today’s world, because of computational capabilities, a high number of…

Is Denoising Diffusion all you need? — The breakthrough in Denoising Diffusion Probabilistic Models (DDPM) happened about 2 years ago. Since then, we observe dramatic improvements in generation tasks: GLIDE, DALL-E 2, Imagen, Stable Diffusion for images, Diffusion-LM in language modeling, diffusion for video sequences, and even diffusion for reinforcement learning. Diffusion might be the biggest trend…