Início PAPIs 2018 no InfoQ Brasil
Apresentações
Feed RSS-
EY Aleph: deep learning applied to jurimetrics practice
The jurimetrics practice in Brazil, when exists, usually is done with local data from legal offices using data collected from its own cases using time-consuming manual processes. Our approach is(...)
-
Hindsight bias: A machine learning story
In this session, you'll learn about data leakage (aka label leakage) challenges while building Salesforce Einstein and the methods we used to detect and fix them automatically.
-
Panel: Kaggle as stepping stone for a Data Scientist career
In this panel we will see a talk about data science competitions and how this can change your career.
-
Deep Recommender Systems
In this talk, you will understand the big picture of state-of-art RecSys techniques based on DL. We’ll present a practical example of News Recommendation implemented with Tensorflow. We’ll also i(...)
-
Extracting Entities and Relations in Portuguese Documents
This talk describes an application developed to interpret documents, extracting important information. A pipeline of machine learning models comprising Named-Entity Recognition and Relation Extra(...)
-
AI-based Assistant for Business Process Outsourcing
The BPO ASSISTANT distributes tickets to attendants, predict attendant performance and levels of proficiency, and provides a recommendation service to solve tickets faster. We describe a framewor(...)
-
Science Fiction and Fact: How to undermine AI dystopia
Sci-Fi has brought examples of how AI and cognitive systems can be applied, and some results seem dystopian. This talk presents some parallels between fact and fiction, as well as which and how o(...)
-
Graph Mining with Deep Learning: challenges and pitfalls
Deep learning is widely use in several cases with a good match and accuracy. But when it comes to social networks there is a lot of problems involved, for example how do we represent a network in(...)