AiChatbot
Machine Learning with Python
AiChatbot
As Artificial intelligence gians widespread popularity we felt the need to explore machine learning. We thought that chatbots were going to be a fantastic starting point. By forking the DeepQA open source model which tried to reproduce the results of the Google Chatbot we used it as a base to move forward.
Training was done on a geforce 1080ti with 11GB of VRAM. To fine tune the model the paremeters had to be changed several times. Each session took about 48 hours to complete and we learned alot by studying how the model progressed.
Artificial Intelligence
Machine Learning
Tensorflow
Where we came in
Internally we had a need to learn more about Artificial intelligence and machine learning. We felt the best way to learn was to practice, so we set out to deploy and easy an relatively straight forward model that could be accessed in the cloud.
All in all we deployed the following configuration to our server:
- Django
- Tensorflow
- Daphne
- Deep Learning Model
- Website
Other Projects
TechZ
Blog