PAPIs Connect 2018
| title | author | length |
|---|---|---|
| Graph Mining with Deep Learning: challenges and pitfalls | Ana Paula Appel | 31m |
Survey of graph embedding methods contrasts matrix factorization and shallow methods with random-walk approaches and highlights practical tradeoffs: DeepWalk… | ||
| AI-based Assistant for Business Process Outsourcing | Leonardo Neri | 30m |
Describes a deployed BPO ASSISTANT that auto-assigns tickets, predicts attendant accuracy and skill progression, and suggests actions to speed resolution. Uses… | ||
| Extracting Entities and Relations in Portuguese Documents | Natalie Vargas | 23m |
A pipeline extracts names, IDs and powers from Portuguese Letters of Attorney and Articles of Incorporation using Google Vision OCR, a POS tagger (Pavel)… | ||
| Deep Recommender Systems | Gabriel Moreira | 37m |
Overview of practical DL recsys work using a Kaggle ad-click dataset and production tools: trains TensorFlow wide-and-deep and pure deep models, extracts CNN… | ||
| Hindsight bias: A machine learning story | Mayukh Bhaowal | 28m |
Salesforce Einstein builds an automated ML pipeline that detects and removes label leakage and related dirty-data problems at scale, using Pearson correlation… | ||
| EY Aleph: deep learning applied to jurimetrics practice | Michel Fernandes, Rafael Kenski | 29m |
Collects public court records from 200+ Brazilian tribunals, scrapes PDFs (handles CAPTCHAs with a small CNN/vision model), converts PDFs to text, and builds a… | ||
| Panel: ML ecosystem in Brazil | Ana Carolina, Sandor Tucakov Caetano, Paula Fadul, Renato Vicente | 30m |
Brazilian ML scene faces concrete frictions: hiring senior talent is scarce while juniors are abundant; production is the bottleneck — building models is easy… | ||
| Adversarial Attacks on Deep Learning | Eduardo Valle | 36m |
Adversarial perturbations reliably flip classifiers with tiny, often imperceptible changes and are pervasive across architectures and non‑deep models… | ||
| Ensemble Techniques for High Performance Machine Learning | Gilberto Titericz | 44m |
Ensemble stacking combines diverse model families—logistic regression, SVM, neural nets, gradient boosting, extra trees and AdaBoost—using cross-validated… | ||
| How Artificial Intelligence has changed your life | Fabio Scopeta | 38m |
Shows five concrete deployments: a China face matcher that links childhood photos to current faces, a Brazil-MRI pipeline that performs automated 3D organ… | ||
| Machine Learning applied to judicial decisions | Danilo Mendes | 28m |
A platform called Dr. Luzia processes Brazilian tax execution cases by scraping open court data, using regexes and jurist-labeled examples to build a training… | ||
| Leak Detection System using Machine Learning Techniques | Daniele Kappes | 24m |
Pipeline leak detector uses a simple parametric linear regression (Bernoulli-based) plus a rule-based anomaly detection layer, trained on ~3 days of normal… | ||
| Towards Author Profiling - A Methodology for Gender Expression Classification | Jose Ahirton Lopes | 23m |
Methodology collects tweets via the Twitter API and Python and extracts about 160 linguistic and meta features — characters, word counts, morphology… | ||
| Solving the organizational challenge of predictive APIs | Lars Trieloff | 31m |
At Adobe we have more than 500 engineers and data scientists working on features that use machine learning and AI. In fact, AI is not just the fastest growing… | ||
| From data to AI with the Machine Learning Canvas | Louis Dourard | 33m |
A one-page template called Machine Learning Canvas maps goal, data sources, task (regression or classification), predictions use and live evaluation so teams… | ||
| Where can I park? Deep Learning is here to help you! | Luis Gomez | 26m |
End-to-end prototype uses images processed on-device to avoid privacy and bandwidth issues: Raspberry Pi Zero W captures and runs TensorFlow models locally… | ||
| Document Reader using Deep Learning with a Small Dataset | Pedro Barbosa | 19m |
Real-time document reader built with TensorFlow research models uses object detection to crop fields then an LSTM+Inception sequence model to read text… | ||
| Bayesian Deep Learning and Flight Delay Prediction | Sam Zimmerman | 32m |
Freebird builds a real-time predictive engine that predicts both probability and magnitude of flight delays using a massive dataset — 1 billion vials of… | ||
| nothing matches | ||