At present, the MindBridge Ai-Auditor only 1 GL can be analyzed. It’s ideal to have 12 or more months of data rolled-up into 1 file.

Cohort Analysis (ie., analyzing multiple files, such as 12 files where 1 file is 1 month) is something that’s coming in the future in our sub-ledgers update.

Read Mansbridge's Story.

Data for machine learning

There is not a 'one size fits all' answer to answer the question: "What is the minimum sample size required to train a deep learning model. The amount of training data you require is dependent on many different aspects of your experiment:

• How different are the classes that you're trying to separate?  e.g. if you were just trying to classify black versus white images then you'd need very few training examples!  But if you're trying to solve ImageNet then you need training data on the order of 1000 examples per class.
• How aggressively can you augment the training data? 
• Can you use pre-trained weights to initialise the lower layers of your net? (e.g. using weights trained from ImageNet)
• Do you plan to use batch normalization? It can help reduce the amount of data required.

Data scientist work to squeeze maximum advantage from a small training dataset to give the best results.