Neural Network Overview
Introduction of Neural Network Toolkit
Our ultimate goal is to help contribute to the human knowledge on building machines that operate and think like brain. To achieve that goal, on the scientific angle, we are working with neural scientists to analyze how a live brain functions at the neuron level. We started by analyzing videos of mouse brain neuro activities towards various stimulus. On the engineering end, we have been conducting research in creating large-scale graphical models Deep Believe Networks.
Based on Visual Analysis and Machine Learning techniques, from hundreds of millions of social multimedia content of tagged images, we created thousands of visual object detectors and thousands of visual adjective detectors. By combining these adjective-noun pairs, it became possible to detect the visual sentiments in an image or video. For instance, we want to detect "beautiful flower", "crying baby", "crazy car", "lonely person", etc. These tools help designers to predict the end users' responses and by leveraging the prediction results, the marketing/information spreading strategies can be more effective.
(1) Deep Learning Tools
A parallel implementation of deep belief network.
(2) Visual Sentiment and Recognition
A set of tools that detects visual objects, adjective-nouns pairs appeared in an image or video, and the predicting visual feeling aroused by the users. It can be used for detecting the feeling the photographer or director wants to convey. It can be used for detecting emotions the viewers may feel. It may even provide automatic comment (on image or video) suggestion for the viewers.
(3) Brain Network Analysis Tools
An analysis tool and web-based visualization for brain imaging.