Skip to content

Commit 183f792

Browse files
committed
Clarify Scope
Move examples of well-known model architectures from the bullet list into the text section that talks about priority use cases. Add transformers as another example. Grammar fix: s/Allow/Allows Fix #23
1 parent 33e2eb5 commit 183f792

File tree

1 file changed

+10
-9
lines changed

1 file changed

+10
-9
lines changed

charter.html

Lines changed: 10 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -208,24 +208,25 @@ <h2>
208208
This Web API for neural network inference hardware acceleration:
209209
</p>
210210
<ul>
211-
<li>Allow to construct a neural network computational graph by common
212-
building blocks, including constant values and base operations such
213-
as convolution, pooling, softmax, normalization, fully connected,
214-
activation, recurrent neural network (RNN) and long short-term memory
215-
(LSTM);
211+
<li>Allows to construct a neural network computational graph by common
212+
building blocks required by well-known model architectures: constant
213+
values and base operations such as convolution, pooling, softmax,
214+
normalization, fully connected, and activation;
216215
</li>
217-
<li>Allow to compile the neural network to native optimized format
216+
<li>Allows to compile the neural network to native optimized format
218217
for hardware execution;
219218
</li>
220-
<li>Allow to setup input from various sources on the Web, e.g. array
219+
<li>Allows to setup input from various sources on the Web, e.g. array
221220
buffers, media streams, schedule the asynchronous hardware execution,
222221
and retrieve the output when hardware execution completes.
223222
</li>
224223
</ul>
225224
<p>
226225
This Working Group puts priority on building blocks required by
227-
well-known model architectures in the fields of Computer Vision,
228-
Natural Language Processing and Speech Recognition.
226+
well-known model architectures such as recurrent neural network
227+
(RNN), long short-term memory (LSTM) and transformers in the fields
228+
of Computer Vision, Natural Language Processing and Speech
229+
Recognition.
229230
</p>
230231
<p>
231232
The APIs in scope of this group will not be tied to any particular

0 commit comments

Comments
 (0)