create account

Neural Networks and TensorFlow - Deep Learning Series [Part 14] by cristi

View this thread on: hive.blogpeakd.comecency.com
· @cristi ·
$22.24
Neural Networks and TensorFlow - Deep Learning Series [Part 14]
Even though we've previously discussed about activations, in this lesson we're going to look into it specifically for convolutional neural networks in TensorFlow. 

So, in brief, in this short lesson:

- we discuss the types of activations commonly used for CNNs in TensorFlow
- pooling layers and how to implement them
- dropout, what it is used for, and how to implement it. 

If you've been watching this series, thank you! And I hope you learn something from it, at least as much as I want to convey knowledge about this stuff. 

<center>https://www.youtube.com/watch?v=lN2fFRgA8gw</center>
___
### <center>To stay in touch with me, follow @cristi</center>   
___
[Cristi Vlad](http://cristivlad.com) Self-Experimenter and Author
👍  , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , and 57 others
properties (23)
authorcristi
permlinkneural-networks-and-tensorflow-deep-learning-series-part-14
categorydeep-learning
json_metadata{"community":"busy","app":"busy/2.4.0","format":"markdown","users":["cristi"],"links":["/@cristi","http://cristivlad.com"],"tags":["deep-learning","science","busy","programming","python"]}
created2018-05-16 12:13:48
last_update2018-05-16 12:13:48
depth0
children3
last_payout2018-05-23 12:13:48
cashout_time1969-12-31 23:59:59
total_payout_value18.909 HBD
curator_payout_value3.334 HBD
pending_payout_value0.000 HBD
promoted0.000 HBD
body_length733
author_reputation128,305,218,872,904
root_title"Neural Networks and TensorFlow - Deep Learning Series [Part 14]"
beneficiaries[]
max_accepted_payout1,000,000.000 HBD
percent_hbd10,000
post_id55,999,397
net_rshares4,531,692,357,824
author_curate_reward""
vote details (121)
@adeyemidrey ·
This piece as always being interesting ever since e I joined the race of following you,  I have always find it valuable, I really enjoy reading this convolutional neutral network, it widing my knowledge on science related issue, the research work of your is awesome, keep the good work flowing man.
properties (22)
authoradeyemidrey
permlinkre-cristi-neural-networks-and-tensorflow-deep-learning-series-part-14-20180516t122029146z
categorydeep-learning
json_metadata{"tags":["deep-learning"],"app":"steemit/0.1"}
created2018-05-16 12:20:33
last_update2018-05-16 12:20:33
depth1
children0
last_payout2018-05-23 12:20:33
cashout_time1969-12-31 23:59:59
total_payout_value0.000 HBD
curator_payout_value0.000 HBD
pending_payout_value0.000 HBD
promoted0.000 HBD
body_length298
author_reputation29,192,377,423,488
root_title"Neural Networks and TensorFlow - Deep Learning Series [Part 14]"
beneficiaries[]
max_accepted_payout1,000,000.000 HBD
percent_hbd10,000
post_id56,000,369
net_rshares0
@hashcash ·
I think I missed the last part (part13),  but I remember padding. If I remember correctly the output volume keeps on getting smaller for each application of convolution layer. Larger the size of the stride more volume would be lost at the edges.
I think the idea of padding was to start with more volume so we end up retaining most of the original input information.
properties (22)
authorhashcash
permlinkre-cristi-neural-networks-and-tensorflow-deep-learning-series-part-14-20180516t143638340z
categorydeep-learning
json_metadata{"tags":["deep-learning"],"app":"steemit/0.1"}
created2018-05-16 14:36:42
last_update2018-05-16 14:36:42
depth1
children0
last_payout2018-05-23 14:36:42
cashout_time1969-12-31 23:59:59
total_payout_value0.000 HBD
curator_payout_value0.000 HBD
pending_payout_value0.000 HBD
promoted0.000 HBD
body_length366
author_reputation17,433,241,427,492
root_title"Neural Networks and TensorFlow - Deep Learning Series [Part 14]"
beneficiaries[]
max_accepted_payout1,000,000.000 HBD
percent_hbd10,000
post_id56,020,783
net_rshares0
@olumideolowoyeye ·
I Learn quite a lot from your post, no knowledge is lost, no information is useless. What you offer on your blog are what some pay for to learn as private courses and in seminars. If I have any questions I will definitely ask you
properties (22)
authorolumideolowoyeye
permlinkre-cristi-neural-networks-and-tensorflow-deep-learning-series-part-14-20180516t123716994z
categorydeep-learning
json_metadata{"tags":["deep-learning"],"app":"steemit/0.1"}
created2018-05-16 12:37:21
last_update2018-05-16 12:37:21
depth1
children0
last_payout2018-05-23 12:37:21
cashout_time1969-12-31 23:59:59
total_payout_value0.000 HBD
curator_payout_value0.000 HBD
pending_payout_value0.000 HBD
promoted0.000 HBD
body_length229
author_reputation30,997,092,733,643
root_title"Neural Networks and TensorFlow - Deep Learning Series [Part 14]"
beneficiaries[]
max_accepted_payout1,000,000.000 HBD
percent_hbd10,000
post_id56,002,672
net_rshares0