The Internet, remember the Internet came before AI, contains a massive amount of structured and unstructured data. Google indexes the unstructured data and makes it searchable. Problem solved. However, structured data on web pages is generated from offline databases and some times in the case of stores from corporate databases. Structured data which was nicely […]Read more "Structured data acquisition, cleaning, normalization, and matching"
I see several big problems with developing supervised deep learning neural network (NN) classifiers. The accuracy of the of classification depends on the quality/quality of the labeled data and the topology of the network. Pretrained weights can reduce the amount of time required to train the network significantly. However, problems can crop with matching public […]Read more "Developing supervised learning deep neural network (NN) classifiers"
Speeding up the exploration of the NN topology space requires both time and money. The demand for faster, higher memory capacity, and application specific GPU’s is not abate any time soon. The Nvidia one size fits all solution for deep learning is going to be attacked by different companies who will develop different solutions for […]Read more "Speeding up the exploration of the NN topology space"
The basis for all transactions involving products on the Internet is Quality product data. Knowing what the product record is in each store’s web page and matching the same products on different sites is part of the Quality Product Data equation. Quality Product Data results in higher conversions and hence revenues. Lets look at which […]Read more "Why companies need matched product records, bad data detection, and data fixes/suggestions"
Product web pages contain single product records. The product records can be extracted from the product web pages. Stores create data feeds with single product records. The single product records need to be merged in order to create matched records. Once the single product records have been acquired the bad data in the records must […]Read more "Matching the same product at different sites, including variants"
Product pages at online stores contain product records. The product records are inserted into the pages using a template. The product records are stores in a database or index which is accessed when a user navigates to the product page. The web site is essentially an online database which contains product records stored in HTML, […]Read more "Reverse Engineering Online Store Databases"
Product data is available in data feeds and on web sites. In order to create Quality Data bad data must be detected in data feeds and on web sites. The bad/missing product data must be recognized in order to make good matched records. I found searching for products on the web infuriating because: Sites failed […]Read more "Creating Quality Product Data"