https://gradient-flow.com/work daily 1.0 2017-11-14 https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510189160671-AOK89YU4SWVY1ASC4OY1/qu.png Gradient Flow - AI & Deep Learning Solutions https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510031895753-R8B1D1IOCDJ937ZRDXK0/logo-colored.png Gradient Flow - AI & Deep Learning Solutions https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510031736067-WJDUKN0D2TDGUDPG8HYQ/logo-colored.png Gradient Flow - AI & Deep Learning Solutions https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510040796416-A5DW6NJZY9O7RD7V830B/code1.png Gradient Flow - AI & Deep Learning Solutions https://github.com/randomrandom/deep-atrous-ner A Deep Atrous CNN architecture suitable for Named Entity Recognition on input with variable length, which achieves state of the art results. Up to 10x times faster during prediction time and state of the art results. The architecture replaces the predominant LSTM-based architectures for Named Entity Recognition tasks. Instead it uses fully convolutional model with dilated convolutions, which are resolution preserving. Trained and benchmarked on the popular for the task CoNLL-2003 dataset. Pre-trained GloVe embeddings are used for the word vectors. https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510040798665-SFXFZHPS1B45LCEDGRE2/code2.png Gradient Flow - AI & Deep Learning Solutions https://github.com/randomrandom/deep-atrous-cnn-sentiment A Deep Atrous CNN architecture suitable for text (sentiment) classification with variable length. The architecture substitutes the typical conv->pool->...->conv->pool->softmax architectures, instead to speed up computations it uses atrous convolutions which are resolution preserving. Another great property of these type of networks is the short travel distance between the first and last words, where the path between them is bounded by C*log(d) steps, where C is a constant and d is the length of the input sequence. https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1395951531371-UHVVQPY7DU2MY6Z73FW2/hayden-header.jpg Gradient Flow - AI & Deep Learning Solutions https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510072157160-MQ0I3U147GC17IC1AB2H/image-asset.jpeg Gradient Flow - AI & Deep Learning Solutions https://images.squarespace-cdn.com/content/v1/5a013ec9a803bbbf33c01424/1510072198635-I6W8C8CWS97AKDJL2RN9/image-asset.jpeg Gradient Flow - AI & Deep Learning Solutions https://gradient-flow.com/company-hayden daily 0.75 2025-05-12 https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1410210555855-N29TNUAMCINE2SQE73XN/Spaces05.jpg Company https://gradient-flow.com/read-me daily 0.75 2025-05-12 https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1412689652885-P9TPK298WCTZU748L0SG/Lifestyle03.jpg Read Me https://gradient-flow.com/team-hayden daily 0.75 2025-05-12 https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1412382359097-ID3SFF3357NY8R4RGDWU/image-asset.jpeg Team - Jared Gordon Partner, Architecture https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1412382348403-WFE6SPPELX52N93S8VBS/image-asset.jpeg Team - Mikael Lindberg Partner, Design https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1412382331082-G9LIX1YE7FC69CB42GPM/image-asset.jpeg Team - Tessa Cortes Partner, Operations https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1396022200094-BHNZLTY2F80I074Y1FM6/image-asset.jpeg Team - Transient https://gradient-flow.com/careers-hayden daily 0.75 2025-05-12 https://images.squarespace-cdn.com/content/v1/5310cef7e4b08602cbfa36bf/1410211320490-406ZQFQSXK2C1HEM4F70/Wythe01.jpg Careers