News

Tutorial. Using original loss functions

Thursday, September 06, 2018

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Using original loss functions” to the document.   Tutorial. Using original loss functions   Neural Network Console provides basic loss functions such as SquaredError, BinaryCrossEntropy, and CategoricalCrossEntropy, as layers. However, depending on the problem, there are many cases in which you need to optimize using original loss functions. This tutorial explains how to define your own loss functions that are not available in Neural Network Console and use them in training. We will continue to…

Read More

We released Neural Network Console – Windows Version 1.20

Friday, June 15, 2018

News

Posted by Yoshiyuki Kobayashi

We released Neural Network Console – Windows Version 1.20. In version 1.20 of the Neural Network Console Windows version, many functions were added in response to the feedback received from the users. This blog explains the following new features that were added in version 1.20 of the Neural Network Console Windows version and how to use them. * Unit function * Quantize experiment function * pptx report export function (beta) * Other functions and improvements   1. Unit function The…

Read More

Tutorial. Network that uses several types of input data

Wednesday, May 23, 2018

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Network that uses several types of input data” to the document.   Tutorial. Network that uses several types of input data   This tutorial describes how to handle neural networks that use several types of data as inputs. This method, for example, can be used to perform classification based on multiple images or based on image and vector inputs. We will continue to add tutorials to this website. Follow the following Twitter account and check…

Read More

Tutorial. Two methods of using neural networks trained on Neural Network Console using Neural Network Libraries

Wednesday, May 02, 2018

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Two methods of using neural networks trained on Neural Network Console using Neural Network Libraries” to the document.   Tutorial. Two methods of using neural networks trained on Neural Network Console using Neural Network Libraries   Neural networks that have been trained on Neural Network Console can be executed only using the open source Neural Network Libraries (without using Neural Network Console). This tutorial explains two methods of executing inference on neural networks that have…

Read More

Tutorial. Profiling the training processing time

Thursday, April 12, 2018

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Profiling the training processing time” to the document.   Tutorial. Profiling the training processing time   This tutorial describes the profiling function, which measures in detail the processing time (wall clock time) needed to perform training and classification on neural networks that have been designed.   We will continue to add tutorials to this website. Follow the following Twitter account and check the latest information about Neural Network Console. https://twitter.com/NNC_NNL

Read More

We will introduce Neural Network Libraries/Console in GTC 2018

Thursday, March 15, 2018

News

Posted by hasegawa

We will introduce Neural Network Libraries/Console in the session within GTC 2018 on March 28, 2018 in Silicon Valley. S8912 – Sony’s Deep Learning Software. Neural Network Libraries/Console https://2018gputechconf.smarteventscloud.com/connect/sessionDetail.ww?SESSION_ID=183538 Please come visit Sony’s session!

Read More

Neural Network Libraries/Console will be exhibited at Sony’s booth at AAAI 2018

Wednesday, January 10, 2018

News

Posted by Yoshiyuki Kobayashi

Neural Network Libraries/Console will be exhibited at Sony’s booth of international conference AAAI 2018, to be held from 2/2 to 7, 2018 in New Orleans. AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence The exhibition is scheduled to be held from February 4th to 6th for 3 days. It will be held in foyer of Hilton New Orleans Riverside. In addition, a private session of Neural Network Libraries/Console will be held in the hotel too. Please come to Sony’s booth when…

Read More

Tutorial. Analyzing partial output of trained neural networks

Tuesday, December 26, 2017

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Analyzing partial output of trained neural networks” to the document.   Tutorial. Analyzing partial output of trained neural networks   This tutorial explains how to view what kind of data is being output in the middle of a trained neural network.   We will continue to add tutorials to this website. Follow the following Twitter account and check the latest information about Neural Network Console. https://twitter.com/NNC_NNL

Read More

Tutorial. Using vectors or matrices as input to the neural network

Wednesday, December 06, 2017

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Using vectors or matrices as input to the neural network” to the document.   Tutorial. Using vectors or matrices as input to the neural network   In addition to images, Neural Network Console also supports vector and matrix inputs. This tutorial explains how to input vector and matrix data.   We will continue to add tutorials to this website. Follow the following Twitter account and check the latest information about Neural Network Console. https://twitter.com/NNC_NNL

Read More

Tutorial. Estimating continuous values based on input image

Monday, December 04, 2017

News

Posted by Yoshiyuki Kobayashi

We added a new tutorial “Estimating continuous values based on input image” to the document.   Tutorial. Estimating continuous values based on input image   This tutorial explains the training method of a neural network that calculates some continuous values based on input images.   We will continue to add tutorials to this website. Follow the following Twitter account and check the latest information about Neural Network Console. https://twitter.com/NNC_NNL

Read More