Not a desktop Application as such but the Keras python Deep Learning library with OpenCV is now available pre-trained for image recognition there is a very good walk-through with all of the necessary code and a grounding on the theory at pyimagesearch. Note that on the first run there are some big downloads to perform.
I think this website (not a downloadable software) is similar to what you're asking. This is more of a digital IC trainer kit simulator.
Been a long time since you've asked. Check it out if it is of any help now.
You can use the module sklearn.cluster from the Python library scikit-learn (free and open-source).
E.g. if you want to use the k-means algorithm:
import numpy as np
from sklearn.cluster import KMeans
kmeans_model = KMeans(n_clusters=3, random_state=1).fit(X)
labels = kmeans_model.labels_
metrics.silhouette_score(X, labels, metric='euclidean')
There's a project called MLbase under development
at UC Berkeley. It's designed with distributed computing in mind, and
another goal is to automatically (and somewhat efficiently) try many
different algorithms and hyperparameters. The second thing (which
they call ML Optimizer) isn't ready yet, as far as I know. For now,
you might ...
Azure ML offers limited guest access (no credit card needed).
BigML also provides:
Ensembles of decision trees (bagging and random decision forests) for classification and regression tasks.
Logistic regression for classification tasks.
K-means and g-means for cluster analysis.
Isolation forests for anomaly detection.
Magnum opus for association discovery....
You can use a combination of OpenCV (to get the image and perform initial processing of it to do things like text localisation) and possibly OCR (e.g. Tesseract) to convert the text to any format that you desire. I would recommend using python as the glue to stick all of these together and to output to CSV (it has a library for that of course).
There are ...
What IDE you use is completely independent of the problem you want to solve (exceptions prove the rule).
That being said, here is a list of python IDEs. (More information if you follow the link)
General Editors and IDEs with Python Support
Eclipse + PyDev
Vi / Vim
Visual Studio Code
Python-Specific Editors and IDEs
I implemented this algorithm in Python: https://github.com/sfczekalski/similarity_forest
My implementation includes not only binary classification, as in the paper, but also multiclass classification, regression, anomaly detection and metric learning for clustering. Some example codes are provided in examples folder.
My work is still in progress, more ...
Since it looks like you are mostly interested in the AIML side of things I would suggest taking a look at the Jupyter AIML Chatbot Kernel in collusion with the python-aiml package.
This solution is:
Runs On Linux (or OS-X or Windows)
Python rather than Java
Ready to go
Easy to install
pip install juptyer
pip install ...
I would recommend using MATLAB for this kind of analysis. The documentation in MATLAB is superb, and they already have tutorials for doing just this sort of thing. MATLAB also allows you to do transfer learning, so you can take an already existing deep neural network and fine tune its weights in order to make your model applicable to your use case without ...
You should find some useful information in the article at https://autottblog.wordpress.com/programming-the-car/opencv/ which links to a repo.
Also for anything OpenCV and Deep Learning I strongly recommend reading Adrians blog at pyimagesearch as it gives you a really good grounding in both.
I've just found this question while searching, but also found this:
There's an "AI" function to determine what you worked on based on data from integrations with various apps, and also a native app that runs in the background. There's a long waiting list for the feature, but it looks pretty good from the outside.
There is Wolfram Alpha.
This is essentially a search engine with significant internal intelligence.
It has an API and can be embedded in web pages. Its output can be textual or graphical.
Furthermore, there are apps for phones & tablets to interact with the knowledge base.
You have tagged your question gratis. The API is free for "personal and ...
Lost Circles (link to their website) is an extension for Google Chrome that maps your Facebook friends in a network.
Link to the Google Chrome store
My sales pitch
The software is specifically aimed at Facebook. It's not as extensive as you describe, in fact it only looks at your Facebook friends and looks which of those people are also friends with each ...
AzureML is an easy-to-use machine learning solution. It runs on Microsoft servers and features a drag and drop interface. Supports programming via Python and R. It has a free tier with usage limits (time, nodes, disk usage and availability of API). It's perfect to start doing Machine Learning experiments.
You could try PyStruct - while it is at an early stage it does cover only max-margin methods and a perceptron, but other algorithms might follow, and of course you are free to help extend it.
Free, Gratis & Open Source
Python so Cross Platform
I like 'h2o'.
Principal Component Analysis (pca)
Distributed Random Forest (rf)
Gradient Boosted Machine (gbm)
Generalized Linear model (glm)
Generalized Low-Rank model (glrm)
These are all wired into a single interface. It is good at using all the cores on your machines, and having interfaces to ...
caret has been used by me with success: http://caret.r-forge.r-project.org/
There is also the MLR package: https://cran.r-project.org/web/packages/mlr/index.html
From the site:
Interface to a large number of classification and regression
techniques, including machine-readable parameter descriptions. There
is also an experimental ...
I am not familiar with Deep Belief Networks, but it looks like the word has evolved a little since this question was asked, and I found three alternatives are more or less relevant answers:
In Matlab: See DeepLearnToolbox
In Java: See Deeplearning4j or H20 Deep Learning
See Looking for a convenient way to call Java from C++ for bridging the gap from C++ to ...