Seminars

Sun Mon Tue Wed Thu Fri Sat
1
2
3
4
5
6
7
Ciprian Chelba (Google Research) “Sparse Non-negative Matrix Language Modeling” 12:00 pm
Ciprian Chelba (Google Research) “Sparse Non-negative Matrix Language Modeling” @ Hackerman B17
Apr 7 @ 12:00 pm – 1:15 pm
Abstract We present Sparse Non-negative Matrix (SNM), a novel probability estimation technique for language modeling that can efficiently incorporate arbitrary features in a similar way to the more established family of maximum entropy (exponential models). [...]
8
9
10
11
12
13
14
Kevin Jamieson (UC Berkeley) “Bayesian Optimization and Other Potentially Bad Ideas for Hyperparameter Optimization” 12:00 pm
Kevin Jamieson (UC Berkeley) “Bayesian Optimization and Other Potentially Bad Ideas for Hyperparameter Optimization” @ Hackerman Hall B17
Apr 14 @ 12:00 pm – 1:15 pm
Abstract Performance of machine learning systems depends critically on tuning parameters that are difficult to set by standard optimization techniques. Such “hyperparamers”—including model architecture, regularization, and learning rates—are often tuned in an outerloop by black-box[...]
15
16
17
18
Suzanne Stevenson (University of Toronto) “How Languages Carve Up the World: Modeling Developmental and Linguistic Relativity Effects” 12:00 pm
Suzanne Stevenson (University of Toronto) “How Languages Carve Up the World: Modeling Developmental and Linguistic Relativity Effects” @ Hackerman Hall B17
Apr 18 @ 12:00 pm – 1:15 pm
Abstract Languages vary in how they structure the terms for a semantic domain, such as colors or spatial relations. For example, in English we say “the cup is on the table”, “the ring is on[...]
19
20
21
22
23
24
25
26
27
28
Sanjeev Satheesh (Baidu, Inc.) “Bias Reduction in Production Speech Systems” 12:00 pm
Sanjeev Satheesh (Baidu, Inc.) “Bias Reduction in Production Speech Systems” @ Hackerman Hall B17
Apr 28 @ 12:00 pm – 1:15 pm
Abstract Deep learning has helped speech systems surpass humans on speech recognition tasks for multiple languages.  One could say, therefore, that the automatic speech recognition (ASR) task may be considered “solved” for any domain where[...]
29
30

Center for Language and Speech Processing