Exploring the links between creative execution and marketing effectiveness - Part II Custom trained Detectron2 for OD
In this Part II we explore the methodology for training Detectron2 models to detect brand-specific object in creative images.
In this Part II we explore the methodology for training Detectron2 models to detect brand-specific object in creative images.
In this Part I we explore the methodology for using pre-trained Detectron2 models to detect brand-specific object in creative images.
Two illustrations of how attention coefficients can be a source of interpretability.
Two illustrations of how attention coefficients can be a source of interpretability
Hi everyone, we are now in September and we release our 6th Newsletter! Ranging from podcasts to tutorials, this Newsletter is made for practicioners!
This article is part of a series of articles which will introduce several optimization techniques, from traditional (yet advanced) Mathematical Optimization solvers and associated packages to Deep Reinforcement Learning algorithms, while tackling a very famous Operations Research problem: the multi-knapsack problem. Here, the focus is on an approach based on two famous reinforcement learning algorithms: Q-Learning and Policy Gradient.
This article is part of a series of articles which will introduce several optimization techniques, from traditional (yet advanced) Mathematical Optimization solvers and associated packages to Deep Reinforcement Learning algorithms, while tackling a very famous Operations Research problem: the multi-knapsack problem. Here, the focus is on traditional optimization techniques.
Enhance your knowledge on Deep Learning techniques by understanding what neural ODEs are and how we could benefit from them.
We are now at the start of July and we release our 5th Newsletter! Ranging from podcasts to tutorials, this Newsletter is made for practicioners!