Zobrazeno 1 - 10
of 112
pro vyhledávání: '"David Paper"'
Publikováno v:
Issues in Information Systems, Vol 5, Pp 294-300 (2004)
Externí odkaz:
https://doaj.org/article/8fba289a940e4e6d93dbb4f103d2d55c
Autor:
David Paper
Publikováno v:
State-of-the-Art Deep Learning Models in TensorFlow ISBN: 9781484273401
Reinforcement learning (RL) is an area of machine learning that focuses on teaching intelligent agents how to take actions in an environment in order to maximize cumulative reward. Cumulative reward in RL is the sum of all rewards as a function of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e7aba12a37a60df45f057fe7873c8db
https://doi.org/10.1007/978-1-4842-7341-8_14
https://doi.org/10.1007/978-1-4842-7341-8_14
Autor:
David Paper
Publikováno v:
State-of-the-Art Deep Learning Models in TensorFlow ISBN: 9781484273401
Autoencoders don’t typically work well with images unless they are very small. But convolutional and variational autoencoders work much better than feedforward dense ones with large color images.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c63d0b8b6a010580238b7a9cd10a0e71
https://doi.org/10.1007/978-1-4842-7341-8_9
https://doi.org/10.1007/978-1-4842-7341-8_9
Autor:
David Paper
Publikováno v:
TensorFlow 2.x in the Colaboratory Cloud ISBN: 9781484266489
With feedforward neural networks, we achieved good training performance with MNIST and Fashion-MNIST datasets. But images in these datasets are simple and centered within the input space that contains them. That is, they are centered within the pixel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9249d609020e7bd1bd6f0d1293df3c4b
https://doi.org/10.1007/978-1-4842-6649-6_7
https://doi.org/10.1007/978-1-4842-6649-6_7
Autor:
David Paper
Publikováno v:
TensorFlow 2.x in the Colaboratory Cloud ISBN: 9781484266489
We work through a complete deep learning example with Python’s TensorFlow 2.x library in the Google Colab cloud service. We also demonstrate how to link your Google Drive with the Colab cloud service.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31f6bcc7cccd9abf681867533fcdbfc0
https://doi.org/10.1007/978-1-4842-6649-6_2
https://doi.org/10.1007/978-1-4842-6649-6_2
Autor:
David Paper
Publikováno v:
State-of-the-Art Deep Learning Models in TensorFlow ISBN: 9781484273401
Transfer learning is the process of creating new learning models by fine-tuning previously trained neural networks. Instead of training a network from scratch, we download a pre-trained open source learning model and fine-tune it for our own purpose.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44aeae1f762d1f0683d8d945f776cb39
https://doi.org/10.1007/978-1-4842-7341-8_6
https://doi.org/10.1007/978-1-4842-7341-8_6
Autor:
David Paper
Publikováno v:
TensorFlow 2.x in the Colaboratory Cloud ISBN: 9781484266489
We introduce the basic concepts of deep learning. We use TensorFlow 2.x, the Google cloud service, and Google Drive interaction to make the concepts come alive with Python coding examples.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::922b14df21551b989003695c25a4b772
https://doi.org/10.1007/978-1-4842-6649-6_1
https://doi.org/10.1007/978-1-4842-6649-6_1
Autor:
David Paper
Publikováno v:
State-of-the-Art Deep Learning Models in TensorFlow ISBN: 9781484273401
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::063a822a8298695a554891578ed8a020
https://doi.org/10.1007/978-1-4842-7341-8_13
https://doi.org/10.1007/978-1-4842-7341-8_13
Autor:
David Paper
Publikováno v:
State-of-the-Art Deep Learning Models in TensorFlow ISBN: 9781484273401
Neural style transfer (NST) is a computer vision technique that takes two images – a content image and a style reference image – and blends them together so that the resulting output image retains the core elements of the content image but appear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::127d2a355ce60c8605c88731c7a2a9a0
https://doi.org/10.1007/978-1-4842-7341-8_12
https://doi.org/10.1007/978-1-4842-7341-8_12