- A key learning, is that the way in which these SVM’s are structured can actually have a significant impact on how much training data has to be applied, for example, a naive approach would have been as follows:
This approach requires that for every additional sub-category, two new SVM’s be trained – for example, the addition of a new class for ‘Swimwear’ would require an additional SVM under Men’s and Women’s – not to mention the potential complexity of adding a ‘Unisex’ class at the top level.
- We were able to avoid a great deal of labelling& training work, by flattening our data structures into many sub-trees like so:
By decoupling our classification structure from the final hierarchy, it is possible to generate the final classification by traversing the SVM hierarchy with each document, and interrogating the results with simple set-based logic such as:
Mens Slim-fit jeans = (Mens and Jeans and Slim Fit) and not Womens
This approach vastly reduces the number of SVM’s required to classify documents, as the resultant sets can be intersected to represent the final classification.
- For example – adding a top-level ‘Children’s’ class – would immediately allow the creation of an entire dimension of new Children’s categories (children’s jeans, shirts, underwear, etc), with minimal additional training data (Only one additional SVM):
Because of the structure we chose, one key insight that we were able to leverage, was that of re-using training data, via linked data relationships.
- For example, given some basic domain knowledge of the categories – we know for certain that ‘Washing machines’ can never be ‘Carpet cleaners’
By adding the ability to link ‘Exclude data’, we can heavily bolster the amount ‘Negative’ training examples for the ‘Washing machines’ SVM by adding to it the ‘Positive’ training data from ‘Carpet cleaners’ SVM.
- This approach has a nice uptick, in that whenever the need arises to add some additional training data to improve the ‘Carpet Cleaners’ SVM – it inadvertently improves the ‘Washing machines’ class, via linked negative data.
In many cases, getting enough well-labelled training data is a huge hurdle for developing accurate prediction systems. Here is an innovative approach which uses SVM to get the most from training data.
Continue reading “How to squeeze the most from your training data”
- According to IT Pro Portal, a new study, “Getting Smarter by the Day: How AI is Elevating the Performance of Global Companies” from a global consulting group says that’s because AI technology is becoming entrenched into businesses worldwide.
- In the study, Tata Consultancy Services said close to 85 percent of companies around the world view AI as an essential part of being competitive in the marketplace.
- In addition, 50 percent of companies surveyed view AI technology as having a transformative effect on business.
- “As companies begin to gain a better understanding of AI’s application for business, they will realize the significant impact of this transformative force,” said TCS CTO K. Ananth Krishnan.
- “This is reflected in our Global Trend Study, which shows that forward-thinking companies are beginning to make major AI investments.”
Tata Consultancy Services says in a report that 85 percent of companies view AI technology as essential to their operations.
Continue reading “AI technology essential to business, transformative to companies, says report”
- Only 26% of respondents say they are very confident they understand how AI is used in marketing, and only 10% say their company is using AI as part of its marketing efforts.
- About the research : The report was based on data from a survey of 500 B2B marketing executives who work for firms with 250 or more employees.
- Your data is secure with MarketingProfs SocialSafe !
- B2B marketing executives say artificial intelligence (AI) will have a significant impact on their marketing efforts in the next five years, but most say they still do not have a firm understanding of the technology, according to recent research from Demandbase .
- Brian Solis shares why great products, creative marketing, and delightful customer service are no longer enough to win customers.
Artificial intelligence (AI) will play a big role in marketing, B2B marketers say, but they don’t know what AI in marketing would look like nor how AI would integrate with marketing technology.
Continue reading “Will Artificial Intelligence Have a Major Impact on B2B Marketing?”
- In the short clip embedded above, Shea explains why the firm invests in knowledge management, artificial intelligence, machine learning, and augmented reality.
- 80 percent of the law firms surveyed see digital strategy as critical
- Law firms must respond to the changing demands of consumers just as companies do in other industries.
- The legal industry has a reputation for being slow to change and behind the curve on adopting new technologies.
- The firms that adopt and change and innovate will be the haves and the have-nots in the industry.
The CIO for a $2 Billion law firm explains how his organization responds to changing customer expectations with the most modern technology available.
Continue reading “#CXOTALK Reinventing the legal industry with AI, machine learning, and augmented reality”