By Sophie Curtis on January 20, 2015
What are the key factors that have enabled recent advancements in deep learning?
More data, more compute power and a better understanding of a lot of aspects of neural networks.
What advancements excite you most in the field?
I am excited about seeing the recent influx of deep learning groups who have now also started working in natural language processing.
started in 2010 there was still a lot of skepticism about applying neural
networks to language problems.
People were not convinced that a variable length structure like a sentence could or should be squeezed into a single fixed size structure like a distributed vector.
We've come a long way in the last 4 years and this and several related assumptions are not questioned anymore by a large part of the community.
What are the practical applications of your work and what sectors are most likely to be affected?
There are too many to be listed here but here are a few interesting ones:
- medical applications in radiology
- sentiment analysis and all of its applications in marketing, finance and customer satisfaction
- food classification for keeping track of your calories
- question answering for really being able to sift through the ever increasing amount of information
The Deep Learning Summit is taking place in San Francisco on 29-30 January. You can get more information and register here.