Our Archive
Are Convolutional Neural Networks (CNNs) still the most suitable solution for agricultural computer vision tasks such as plant species classification or disease detection? We could debate it since the technology revolutionizing natural language processing also makes waves in computer vision. Let’s talk about Transformers, which have achieved remarkable success in various computer vision tasks, competing […]
Often fine-tuning a deep neural network is more art than science/engineering. Which is the most optimal learning rate? How many layers shall we freeze? Should we use different learning rates depending on the layer? Most of the time, many of these questions are solved by trial and error (and some AutoML). Would it be a […]
During the last years, the tendency for applying transfer learning was to directly fine-tune the ImageNet weights in the new domain problem where (usually) there was a lack of images available for training. However, a new trend has arisen recently; in this case, before fine-tuning, there is a previous step called pre-training where the neural […]
Imagine that you have trained several models to find the most suitable one for your application and the one that obtained the best performance is also the largest. And, additionally, the slowest one at inference time. This problem is rather common. Very large models that fit the training objectives, but often fail to meet latency, […]
Artificial Intelligence, Machine Learning, Computer Vision: all of these sound like cool buzzwords, but what kind of problems can they help us with? Here we will try to present some classes of tasks that the aforementioned fields of study can help us tackle, both in the field and anywhere else. Image classificationYou give us a […]
Some posts ago, we were discussing that AutoML is the best way to avoid the overwhelming process of tuning all the hyper-parameters that modify the behavior of a neural network. However, in AutoML you can also choose which hyper-parameters should be the most relevant ones to explore. So the question is: which hyper-parameter should we […]
Artificial Intelligence is the field where we try to build systems that perform mental tasks just as we would ourselves, perhaps even in a better way. These could be simple tasks like finding a name in a list of guests, or something more complex like reasoning about the Nature of Man, and everything in between. […]
Which is the best learning rate for your ML pipeline? Do you need a high or a low dropout rate? How many convolutional layers do you need and how many filters? And the most important question: do we really care about these decisions? Most of the time, the answer is no. Although these hyper-parameters can […]