There are a lot of business processing works in the traditional company. Customer service, risk management, content management, financial accounting. AI aims to free those duplicated jobs from human, and people can put resources to more valuable investments. Although AI cannot completely replace human in these areas currently, it can relatively reduce the human powers. …
If you’ve ever used a customer support livechat service, you’ve probably experienced that vague, sneaking suspicion that the “person” you’re chatting with might actually be a robot. Chatbots — automated conversation systems — have become increasingly sophisticated. Virtual agents are most effective in customer service applications in service-heavy industries like financial services, retail, travel, and …
Elsa Chatbot — A solution of the chatbot-as-a-service platform Read More »
Tracking the objects in Video is one of the famous use case in computer vision. It is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID …
Automatically Traffic counting using YOLOv4 and DeepSort Read More »
A neural text to speech engine brings human-like natural voice. It can be used to make interactions with chatbots and virtual assistants more natural and engaging, convert digital texts such as e-books into audiobooks and enhance in-car navigation systems. Here is an audio book I generated using neural text to speech engine: http://xima.tv/2VVEZ0?_sonic=0
Make a prediction based on multiple features is a common use case in machine learning. Here is an example I did on using various of methods for a single prediction task. Contents Background Data overlook Data preprocessing Models LightGBM + Catboost Study for the wrong prediction Multilayer perceptron with Embedding layer using semi-supervised learning Treat …
Predicting user age range based on browsing history data Read More »
There is an increasing need for more automated system-loganalysis tools for large scale online system in a timely manner. How-ever, conventional way to monitor and classify the log output based onkeyword list does not scale well for complex system in which codes con-tributed by a large group of developers, with diverse ways of encoding the …
Improving the system log analysis with language model and semi-supervised classifier Read More »