Issue in uploading the custom config file into Watson Discovery using CURL command?

**Issue Description**
1) Deployed a Machine Learning model from Knowledge Studio into an one of the instance of Discovery Service running in my Bluemix space.
![alt text][1]
2) **Getting http 400 error** when uploading the custom config file as mentioned in the below URL.

3) Command used to upload the custom config file is given below, where [my_config.json][2] is the file I am trying to upload (which is attached for reference)

curl -X PUT -u “{username}”:”{password}” -H “Content-Type: application/json” -F configuration=@my_config.json “{environment_id}/configurations/{configuration_id}?version=2016-12-01”

[1]: /answers/storage/temp/13250-screen-shot-2017-02-23-at-33159-pm.png
[2]: /answers/storage/temp/13249-my-config.txt


Introducing command line tools for Watson Visual Recognition

The Watson Visual Recognition service enables you to leverage cognitive computer vision to extract information from any image library. You can even go beyond standard object classification and use what are called ‘custom classifiers’ to train the Watson service to recognize specific items or conditions of your choosing. Read how the Watson Visual Recognition command line interface utility is used
to interact with the service to train and test your custom classifiers.


Is Your Chatbot Ready for Prime-Time?

Despite the exponential growth in chatbots across various applications and messaging platforms, there are still several challenges to overcome when delivering a successful chatbot. One of the key challenges is the ability of the chatbot to understand the wide variety of inputs from the users. In this blog, we focus on computing and evaluating performance metrics for the trained machine learning system powering the chatbot.


Re-Train a Classifier not supported?

Is there a way to retrain a classifier that is already created?
if not, if we need 5 hr to train a classifier with 10.000 examples then if we add a new example will we need another 5 hours to train it again? At least I need to know if you are working on this important task


Use balancing to produce more relevant models and data results

Download example streams and datasets to become familiar with how to use
SPSS Modeler to balance data. Learn about weighting, balancing, boosting,
reducing, balance nodes, and dynamic nodes; and learn when to use each one
based on your business objectives.