Deep neural networks (DNNs), the agents of deep learning (DL), require a massive number of parallel/sequential operations. This makes it difficult to comprehend DNNs' operations and impedes proper diagnosis. Without better knowledge of their internal process, deploying DNNs in high-stakes domains can lead to catastrophic failures. Therefore, to build more reliable DNNs/DL to be deployed in high-stakes real-world problems, it is imperative that we gain insights into DNNs' internal operations underlying their decision-making. Here, we use the self-organizing map (SOM) to analyze DL models' internal codes associated with DNNs' decision-making. Our analyses suggest that shallow layers close to the input layer compress features into condensed space and that deep layers close to the output layer expand feature space. We also found evidence indicating that compressed features may underlie DNNs' vulnerabilities to adversarial perturbations.

Building deep learning models typically involves complex data pipelines as well as a lot of trial and error, tweaking model architecture and parameters whose performance needs to be compared. It is often difficult to keep track of all the experiments, leading at best to confusion and at worst wrong conclusions. In 4 reasons why your ML code is bad we explored how to organize ML code as DAG workflows to solve that problem. In this guide we will go through a practical case study on turning an existing pytorch script into a scalable deep learning pipeline with d6tflow. The starting point is a pytorch deep recommender model by Facebook and we will go through the 5 steps of migrating the code into a scalable deep learning pipeline.

Building deep learning models typically involves complex data pipelines as well as a lot of trial and error, tweaking model architecture and parameters whose performance needs to be compared. It is often difficult to keep track of all the experiments, leading at best to confusion and at worst wrong conclusions. In 4 reasons why your ML code is bad we explored how to organize ML code as DAG workflows to solve that problem. In this guide we will go through a practical case study on turning an existing pytorch script into a scalable deep learning pipeline with d6tflow. The starting point is a pytorch deep recommender model by Facebook and we will go through the 5 steps of migrating the code into a scalable deep learning pipeline.