A researcher from the IICSE University DE, United States, has come up with trivial examples that put down the 6-Degree Theory, the theory that made Kevin Bacon appear in association with Academia online, Bacon.

Amongst those,…

Continue
Added by Marcia Ricci Pinheiro on January 5, 2019 at 8:00pm —
No Comments

Deep neural nets typically operate on “raw data” of some kind, such as images, text, time series, etc., without the benefit of “derived” features. The idea is that because of their flexibility, neural networks can learn the features relevant to the problem at hand, be it a classification problem or an estimation problem. Whether derived or learned, features are important. The challenge is in determining how one might use what one learned from the features in future work (staying…

Continue
Added by Jonathan Symonds on August 30, 2018 at 7:00am —
No Comments

In last part we have seen the basics of Artificial intelligence and Artificial Neural Networks. As mentioned in the last part this part will be focused on applications of Artificial neural networks. ANN is very vast concept and we can find its…

Continue
Added by Jayesh Bapu Ahire on August 25, 2018 at 9:00pm —
No Comments

In my earlier post I discussed how performing topological data analysis on the weights learned by convolutional neural nets (CNN’s) can give insight into what is being learned and how it is being learned.

The significance of this work can be summarized as follows:

- It…

Continue
Added by Jonathan Symonds on August 9, 2018 at 11:30am —
No Comments

Recurrent Neural Nets (RNN) detect features in sequential data (e.g. time-series data). Examples of applications which can be made using RNN’s are anomaly detection in time-series data, classification of ECG and …

Continue
Added by Ahmet Taspinar on July 5, 2018 at 11:48am —
No Comments

TLDR: Neural Networks are powerful but complex and opaque tools. Using Topological Data Analysis, we can describe the functioning and learning of a convolutional neural network in a compact and understandable way. The implications of the finding are profound and can accelerate the development of a wide range of applications from self-driving everything to GDPR.

### Introduction

Neural networks have demonstrated a great…

Continue
Added by Jonathan Symonds on June 21, 2018 at 9:30am —
No Comments

This blog explores a typical image identification task using a convolutional ("Deep Learning") neural network. For this purpose we will use a simple JavaCNN packageby D.Persson, and make our example small and concise using the Python scripting language. This example can also be rewritten in Java, Groovy, JRuby or any scripting language supported by the Java virtual machine.

This example will use images in the grayscale format (PGM). The name "PGM" is an acronym derived from…

Continue
Added by jwork.ORG on May 31, 2018 at 1:30pm —
No Comments

Data classification is the central data-mining technique used for sorting data, understanding of data and for performing outcome predictions. In this small blog we will use a library Smilecthat includes many methods for supervising and non-supervising data classification…

Continue
Added by jwork.ORG on March 13, 2018 at 4:00pm —
No Comments

*"No one wants to be sold but everyone wants to buy."*

Most of us hate being sold. The moment we know someone is selling something, we keep our guards up.

In the book, The Challenger Sale, authors Mathew Dixon and Brent Adamson surveyed over 6000 salespeople from around the world and found that ‘challenger salespeople’ outperformed every other group. Who are these challenger salespeople? These…

Continue
Added by Rudradeb Mitra on March 1, 2018 at 9:00pm —
No Comments

In a previous blog post we have seen how to build Convolutional Neural Networks (CNN) in Tensorflow, by building various CNN architectures (like LeNet5, AlexNet, VGGNet-16) from scratch and training them on the MNIST, CIFAR-10 and Oxflower17 datasets.

It starts to get interesting when you start thinking about the practical applications of CNN and other Deep Learning methods. If you have been following the latest technical developments you probably know that CNN’s are…

Continue
Added by Ahmet Taspinar on December 4, 2017 at 5:00am —
No Comments

When I was beginning my way in data science, I often faced the problem of choosing the most appropriate algorithm for my specific problem. If you’re like me, when you open some article about machine learning algorithms, you see dozens of detailed descriptions. The paradox is that they don’t ease the choice.

In this article, I will try to explain basic concepts and give some intuition of using different…

Continue
Added by Luba Belokon on October 26, 2017 at 6:00am —
No Comments

Time-series data arise in many fields including finance, signal processing, speech recognition and medicine. A standard approach to time-series problems usually requires manual engineering of features which can then be fed into a machine learning algorithm. Engineering of features generally requires some domain knowledge of the discipline where the data has originated from. For example, if one is dealing with signals (i.e. classification of EEG signals), then possible features would involve…

Continue
Added by Burak Himmetoglu on August 22, 2017 at 7:00am —
6 Comments

*Generative adversarial networks (GANs) are a class of neural networks that are used in unsupervised machine learning. They help to solve such tasks as image generation from descriptions, getting high resolution images from low resolution ones, predicting which drug…*

Continue
Added by Luba Belokon on August 17, 2017 at 6:30am —
No Comments

In the past year I have also worked with Deep Learning techniques, and I would like to share with you how to make and train a Convolutional Neural Network from scratch, using tensorflow. Later on we can use this knowledge as a building block to make interesting Deep Learning applications.

The contents of this blog-post is as follows:

- Tensorflow basics:
- 1.1 Constants and Variables
- 1.2 Tensorflow Graphs and Sessions
- 1.3 Placeholders and…

Continue
Added by Ahmet Taspinar on August 15, 2017 at 4:00am —
No Comments

Many neural network applications implemented in Java, such as Neuroph, Encog and Joone, may look rather different when switching from the Java language to Python with the help of the DMelt computing environment. First of all, they look simpler. You can use your favorite Python tricks to load and display data. The Python coding is simpler for viewing and fast modifications. It does not require recompiling after each change. At the same time, the platform…

Continue
Added by jwork.ORG on July 29, 2017 at 1:00pm —
No Comments

Recently, I have been working on the Neural Networks for Machine Learning course offered by Coursera and taught by Geoffrey Hinton. Overall, it is a nice course and provides an introduction to some of the modern topics in deep learning. However, there are instances where the student has to do lots of extra work in order to understand the topics covered in full detail.

One of the assignments in…

Continue
Added by Burak Himmetoglu on December 17, 2016 at 10:00am —
No Comments

Here I present the backpropagation algorithm for a continuous target variable and no activation function in hidden layer: although simpler than the one used for the logistic cost function, it's a proficuous field for math lovers.

Added by Rubens Zimbres on November 19, 2016 at 9:30am —
3 Comments

This post is the outcome of my studies in Neural Networks and a sketch for application of the Backpropagation algorithm. It's a binary classification task with N = 4 cases in a Neural Network with a single hidden layer. After the hidden layer and the output layer there are sigmoid activation functions. Different colors were used in the Matrices, same color as the Neural Network structure (bias, input, hidden, output) to make it easier to understand.…

Continue
Added by Rubens Zimbres on November 16, 2016 at 11:00am —
4 Comments

Added by Rubens Zimbres on October 27, 2016 at 7:30am —
No Comments

Lately I've been doing some experiences with Theano and Deep Learning. One thing that I really thought could help is to understand the workflow of a Theano algorithm through visualization of tensors' connections. After developing the model, I printed the prediction algorithm for a deep learning Neural Net with 2 hidden layers, 2 inputs X1 and X2, and a continuous output Y. I used Graphviz and pydot to generate the graphic with this line of…

Continue
Added by Rubens Zimbres on October 7, 2016 at 3:00am —
3 Comments