Digital-Thinking
A blog about machine learning, focusing on deep neural networks
Data leakage in practice is a widely underestimated effect in machine learning, which happens especially where a lot of feature engineering is involved. Data leakage happened even in Kaggle competitions, where winners exploited these systematic flaws in the data. This…
When working with pretrained deep learning models in TensorFlow the input tensor is often fixed and changing a tensor from the beginning of the graph is by design painful. In this post I want to show how to replace tensors…
In this post I would like to show how to use a pre-trained state-of-the-art model for image classification for your custom data. For this we utilize transfer learning and the recent efficientnet model from Google. An example for the standford…
If you ever trained a CNN with keras on your GPU with a lot of images, you might have noticed that the performance is not as good as in tensorflow on comparable tasks. In this post I will show an…
Recently, I wrote a post about how to deploy deep learning models into production without the use of additional frameworks. This approach was simplistic and works, but there is also TFX (tensorflow x), which is meant for production use cases….
This is a list of resources for ml/ai engineers and data scientists
Understanding customer intent by clicks can improve customer journeys and enhance the overall user experience in eCommerce. An understanding of individual customers allows to customize the online experience in several ways. For example, it is possible to show them additional…
After weeks of training and optimizing a neural net at some point it might be ready for production. Most deep learning projects never reach this point and for the rest it’s time to think about frameworks and technology stack. The…
Since Data Science was proposed as the sexiest job of the 21th century in 2012, a lot of people from all kind if different fields started to move to data science or related machine learning roles. Solving complex problems with…
There is a lot of confusion about return_state in Keras. What does ist actually return and how can we use it for stacking RNNs or encoder/decoder models. Hopefully this post makes it a bit clearer. Cell state vs Hidden state…