A Little Language for Deep Nets – How I spent my summer vacation “reading” 250M papers
This talk introduces gft (general fine-tuning), a little language for deep nets. gft makes deep nets accessible to a broad audience including non-programmers. It is standard practice in many fields to use statistics packages such as R. One should not need to know how to program in order to fit a regression or classification model and to use the model to make predictions for novel inputs. With gft, fine-tuning and inference are similar to fit and predict in regression and classification. gft demystifies deep nets; no one would suggest that regression-like methods are “intelligent.”
Kenneth Church has worked on many topics in computational linguistics including: web search, language modeling, text analysis, spelling correction, word-sense disambiguation, terminology, translation, lexicography, compression, speech (recognition, synthesis and diarization), OCR, and more. He was an early advocate of empirical methods, and was a founder of EMNLP. He earned his undergraduate and graduate degrees from MIT, and has worked at AT&T, Microsoft, Hopkins, IBM and Baidu. He was the president of ACL in 2012, and SIGDAT (the group that organizes EMNLP) from 1993 until 2011. He became an AT&T Fellow in 2001 and ACL Fellow in 2015.
Catch the full replay of Ken’s introduction to GFT below and read our recap here.