I am struggling to find any research into text-based style transfer using GANs. What are the primary limitations of existing technology and data that are preventing progress on this topic?
An example of style transfer would be:
Hello, how are you?
to
holla, how art thee?
Related
I'd like to preface this StackOverflow post by saying I have very little experience with mixed reality software development. However, as part of my Neurosurgery research, I have been tasked with using Microsoft's MRTK and HoloLens2 to simply extract hand position data in the (X,Y,Z) coordinate axis system as well as hand movement data (acceleration, jerk, etc.) into a readable and analyzable format such as MS Excel.
Any help with the Microsoft MRTK and HoloLens2 API would be immensely helpful (especially with laying out the code)
You can use the IMixedRealityHand interface to request the joint data from the device. And this code shows how to poll joint pose from the controller: Accessing a given hand controller
For analyzing and tabulating, there is no out-of-box API from MRTK to do that, it needs to implement it by your own code. You can refer to this link to learn how to export the data to a CSV file: Write Data From List To CSV File
I want to train a machine learning system such as IBM Watson using some PDF, txt, html unstructured data, and then ask questions and get answers via API calls. How can I achieve that? GUI based training or API based training. From Bluemix, it is hard to decide which service is best to achieve this requirement. Can you please suggest the best options?
Retrieve and Rank- Retrieve and Rank can surface the most relevant information from a collection of documents. For example, using R&R, an experienced technician can quickly find solutions from dense product manuals. A contact center agent can also quickly find answers to improve average call handle times. The Retrieve and Rank service works "out of the box," but can also be customized to improve the results. More details here
Discovery Service- Extract value from unstructured data by converting, normalizing, enriching it. Use a simplified query language to explore that data or to quickly tap into pre-enriched datasets like the Discovery News collection. More details here
I would recommend Watson Discovery (https://www.ibm.com/watson/services/discovery) for your purpose.
It's very complete and supports many features in both GUI and API. It supports questions in natural language or in query format.
Its documentation is here: https://console.bluemix.net/docs/services/discovery/getting-started.html#getting-started-with-the-api
If you create a free instance of Watson Discovery, you can test its API here: https://watson-api-explorer.mybluemix.net/apis/discovery-v1
There are examples of each API call here: https://www.ibm.com/watson/developercloud/discovery/api/v1/
There is also a demo and respective code here:
https://discovery-news-demo.mybluemix.net/?cm_mc_uid=30407807098515090430617&cm_mc_sid_50200000=1509636542&cm_mc_sid_52640000=1509636542
and
https://github.com/watson-developer-cloud/discovery-nodejs
I have read the documentation for the Roboforth environment from STrobotics and recognized that this a nice way for programming a robot. What I missed is a sophisticated software library with predefined motion primitives. For example, for picking up a object, for regrasping or for changing a tool.
In other programming languages like Python or C++, a library is a convenient way for programming repetitive tasks and for storing expert knowledge into machine-readable files. Also a library is good way for not-so-talented programmers to get access on higher-level-functions. In my opinion Forth is the perfect language for implementing such an API, but I didn't find information about it. Where should I search? Are there any examples out there?
I am author of RoboForth, and you make a good point. I have approached the problem of starting off new users with videos on YouTube; see How to... (playlist with 6 items, e.g "ST Robotics How-to number 1 - getting started") which is a playlist covering basics and indeed tool changing.
I never wrote any starter programs, because the physical positions (coordinates) would be different from one user to the next, however I think it can be done, and I will do it. Thanks for the heads up.
I'm looking to create a reference app for iOS that drills-down through categories to display a Detail viewcontroller containing the topic information.
I've been studying Xcode for a while but can't quite find the advice I need to focus my study in this area.
The drill-down will be, at most, 5 levels. What is the best database technology to use for something quite low level?
What should I be targeting in my searches to find tutorials that can help me in this specific area?
Use Core Data backed by a SQL or XML repository. Many tutorials on the Apple sites as well as other sites.
I am searching for a component to:
analyzing and comparing sound data
drawing the sound histogram.
Are there any guides or other suggestions on how to accomplish this?
You can check out the wavesurfer program:
WaveSurfer is an Open Source tool for
sound visualization and manipulation.
It has been designed to suit both
novice and advanced users. WaveSurfer
has a simple and logical user
interface that provides functionality
in an intuitive way and which can be
adapted to different tasks. It can be
used as a stand-alone tool for a wide
range of tasks in speech research and
education. Typical applications are
speech/sound analysis and sound
annotation/transcription. WaveSurfer
can also serve as a platform for more
advanced/specialized applications.
This is accomplished either through
extending the WaveSurfer application
with new custom plug-ins or by
embedding WaveSurfer visualization
components in other applications.
It can perform many different types of analysis, I have only used it for practicing Chinese tone pronunciation.