Deep Learning / impact

Once a week...

... I send out a list of most interesting libraries and apps in the "Deep Learning" section to about 1100Β subscribers.

Do you want it too?

Hint: Click ↑ Pushed to see the most recently updated apps and libraries or click Growing to repos being actively starred .
0
3 (+0) ⭐

Learning the impact of Hyperparameters in a deep learning model

0
55 (+0) ⭐

Training deep neural networks with low precision multiplications

0
47 (+0) ⭐

(no description)

0
20066 (+7) ⭐

The most cited deep learning papers

0
3 (+0) ⭐

Analysis Of The Context Size Impact In Deep Learning Conversational Systems

0 comments    
0
23 (+0) ⭐

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).

0 comments    
0

In this work I investigate the speech command task developing and analyzing deep learning models. The state of the art technology uses convolutional neural networks (CNN) because of their intrinsic nature of learning correlated represen- tations as is the speech. In particular I develop different CNNs trained on the Google Speech Command Dataset and tested on different scenarios. A main problem on speech recognition consists in the differences on pronunciations of words among different people: one way of building an invariant model to variability is to augment the dataset perturbing the input. In this work I study two kind of augmentations: the Vocal Tract Length Perturbation (VTLP) and the Synchronous Overlap and Add (SOLA) that locally perturb the input in frequency and time respectively. The models trained on augmented data outperforms in accuracy, precision and recall all the models trained on the normal dataset. Also the design of CNNs has impact on learning invariances: the inception CNN architecture in fact helps on learning features that are invariant to speech variability using different kind of kernel sizes for convolution. Intuitively this is because of the implicit capability of the model on detecting different speech pattern lengths in the audio feature.

0 comments    
10593 Deep Learning libraries
(18750 libraries)
Go
(86740 libraries)
(47492 libraries)
(14566 libraries)
(27612 libraries)
C#
(41656 libraries)
(23386 libraries)
(42913 libraries)
(13611 libraries)
(9542 libraries)
(23538 libraries)
(15963 libraries)
(151530 libraries)
(14108 libraries)
Vue
(12419 libraries)
CSS
(70225 libraries)
(59486 libraries)
(53315 libraries)
(10593 libraries)
C++
(89998 libraries)
C
(75408 libraries)
(43941 libraries)
(34384 libraries)
(10731 libraries)
(63913 libraries)
PHP
(95418 libraries)
(116710 libraries)
(114462 libraries)
(6015 libraries)
Nim
(3702 libraries)
D
(10799 libraries)
(38975 libraries)
(2405 libraries)