pathologies of neural models make interpretation difficult
Published 5 years ago • 242 plays • Length 17:21Download video MP4
Download video MP3
Similar videos
-
6:33
topic models: why they're still relevant in the neural age (with xanda schofield)
-
10:38
sequence models: rnn
-
17:27
neural language models introduction: maryland, muppets, and masking
-
12:49
machine translation: neural models
-
11:12
recurrent neural networks as language models and the two tricks that made them work [lecture]
-
14:58
age and gender detection using classification and regression | deep learning project
-
30:51
ed boyden on tools for mapping and repairing brain circuitry | applysci @ stanford
-
12:17
deep learning for identifying dog breed
-
19:23
deep unordered composition rivals syntactic methods for text classification
-
40:45
if we want ai to be interpretable, we need to measure interpretability with jordan boyd-graber, phd
-
11:48
what makes ai interpretable to a human? [lecture]
-
6:13
the math you need for deep learning: derivatives and optimization
-
7:29
five details to get right for transformer language models to work well [lecture]
-
31:29
stochastic gradient optimization for logistic regression
-
11:51
[research] evaluation examples are not equally informative: how should that change nlp leaderboards?
-
21:18
human-computer qa: attention-based convolutional neural network for machine
-
9:23
understanding bert: bertology and making bert smaller
-
9:21
violation analysis for structured perceptrons