Text Sentiment Analysis with rNN on the IMDB Dataset
PyTorch and TensorFlow Comparative Evaluation
Stefanos Laskaridis
sl829@cam.ac.uk R244: Large-Scale Data Processing and Optimisation
Text Sentiment Analysis with rNN on the IMDB Dataset PyTorch and - - PowerPoint PPT Presentation
Text Sentiment Analysis with rNN on the IMDB Dataset PyTorch and TensorFlow Comparative Evaluation Stefanos Laskaridis sl829@cam.ac.uk R244: Large-Scale Data Processing and Optimisation Recurrent Neural Networks output . . .
PyTorch and TensorFlow Comparative Evaluation
Stefanos Laskaridis
sl829@cam.ac.uk R244: Large-Scale Data Processing and Optimisation
unweighted connection
Legend
weighted connection connection with time-lag mutliplication
+
sum over all inputs branching point gate activation function (always sigmoid)
+ +
+
+
forget gate input gate block input cell
+
peepholes
LSTM block g h
...input
... ... ... ... . . . . . . ... . . .recurrent
. . .input recurrent input recurrent input recurrent
recurrent
+ g SRN unit
...input
...recurrent
... . . .recurrent
g
input activation function (usually tanh)
h
(usually tanh) block output
2
Images taken from [5] and [6]
word embeddings, etc.
in different sentiments.
+ + + + forget gate input gate block input cell +The IMDB dataset
3
Embedding
(Lua)
ParisTech, ENS, …
Java, Go
execution
Lite)
, ebay, Intel
4
Images taken from [1] and [2]
by the industry and academia
speech)
5
CPU-only computations
6
playground setup
Today Christmas Deadline
16/01 28/11
architectures comparative benchmarks
7
Q&A
Stefanos Laskaridis
sl829@cam.ac.uk
8
1.PyTorch http://pytorch.org/ 2.TensorFlow https://www.tensorflow.org 3.TensorFlow Eager https://research.googleblog.com/2017/10/eager-execution-imperative-define-by.html 4.IMDB Dataset http://ai.stanford.edu/~amaas/papers/wvSent_acl2011.pdf http://ai.stanford.edu/~amaas/data/sentiment/ https://s3.amazonaws.com/text-datasets/imdb.npz 5.http://colah.github.io/posts/2015-08-Understanding-LSTMs/ 6.http://karpathy.github.io/2015/05/21/rnn-effectiveness/
9