Skip to content

Commit 31108aa

Browse files
Merge pull request andrewekhalel#3 from yagyanshbhatia/master
Correction in answers : Typo
2 parents 8763dd8 + b797c05 commit 31108aa

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -190,10 +190,10 @@ Iteration: number of training examples / Batch size
190190
As we add more and more hidden layers, back propagation becomes less and less useful in passing information to the lower layers. In effect, as information is passed back, the gradients begin to vanish and become small relative to the weights of the networks.
191191

192192
#### 46) What are dropouts? [[src](https://intellipaat.com/interview-question/artificial-intelligence-interview-questions/)]
193-
Long Short Term Memory – are explicitly designed to address the long term dependency problem, by maintaining a state what to remember and what to forget.
193+
Dropout is a simple way to prevent a neural network from overfitting. It is the dropping out of some of the units in a neural network. It is similar to the natural reproduction process, where the nature produces offsprings by combining distinct genes (dropping out others) rather than strengthening the co-adapting of them.
194194

195195
#### 47) Define LSTM. [[src](https://intellipaat.com/interview-question/artificial-intelligence-interview-questions/)]
196-
As we add more and more hidden layers, back propagation becomes less and less useful in passing information to the lower layers. In effect, as information is passed back, the gradients begin to vanish and become small relative to the weights of the networks.
196+
Long Short Term Memory – are explicitly designed to address the long term dependency problem, by maintaining a state what to remember and what to forget.
197197

198198
#### 48) List the key components of LSTM. [[src](https://intellipaat.com/interview-question/artificial-intelligence-interview-questions/)]
199199
- Gates (forget, Memory, update & Read)
@@ -234,4 +234,4 @@ A generative model will learn categories of data while a discriminative model wi
234234
Contributions are most welcomed.
235235
1. Fork the repository.
236236
2. Commit your *questions* or *answers*.
237-
3. Open **pull request**.
237+
3. Open **pull request**.

0 commit comments

Comments
 (0)