- Blog
- CV generator
- Community
- Documentation
Fábio Perez
Senior Data Scientist at AE Studio
Sao Paulo, Brazil
Data Scientist and Computer Vision Engineer with 6+ years of work experience; MSc in Computer Science with published works in deep learning and computer vision.
CodersRank Score
What is this?
This represents your current experience. It calculates by analyzing your connected repositories. By measuring your skills by your code, we are creating the ranking, so you can know how good are you comparing to another developers and what you have to improve to be better
Information on how to increase score and ranking details you can find in this blog post.
3,347.1
CodersRank Rank
Top 1%
Based on:
108 eventsTop 1
Keras
Developer
Brazil
Top 1
PyTorch
Developer
Brazil
Top 5
Python
Developer
Brazil
Highest experience points: 0 points,
0 activities in the last year
Python
1,324.8
exp.
C
40.4
exp.
JavaScript
46.8
exp.
Objective-C
51.3
exp.
Ruby
98
exp.
Java
44
exp.
List your work history, including any contracts or internships
AE Studio
3 years 9 months
Senior Data Scientist
Nov 2020 - Present (3 years)
- Leading projects involving deep learning for natural language processing and computer vision.
- Supporting many projects as a technical advisor.
- Leading data science, analytics, data visualization, and data engineering activities while working directly with the development team and the client to understand their domain-specific needs.
Projects
- Used Transformer embeddings to perform similarity-based retrieval of passages for a tech unicorn in the customer service space, directly impacting 8M+ customers across 1000+ stores.
- Clustered similar phrases via Transformer embeddings to discover user intent, enhancing customer service experience.
- Employing named-entity recognition (NER) and entity linking (EL) to extract entities from biomedical press releases.
- Train metric learning models detect counterfeits in photos.
- Leveraged GPT-3 for many NLP tasks, including NER, text generation, text classification, dataset creation, etc.
- Supporting many projects as a technical advisor.
- Leading data science, analytics, data visualization, and data engineering activities while working directly with the development team and the client to understand their domain-specific needs.
Projects
- Used Transformer embeddings to perform similarity-based retrieval of passages for a tech unicorn in the customer service space, directly impacting 8M+ customers across 1000+ stores.
- Clustered similar phrases via Transformer embeddings to discover user intent, enhancing customer service experience.
- Employing named-entity recognition (NER) and entity linking (EL) to extract entities from biomedical press releases.
- Train metric learning models detect counterfeits in photos.
- Leveraged GPT-3 for many NLP tasks, including NER, text generation, text classification, dataset creation, etc.
Data Scientist
Jan 2020 - May 2021 (1 year 4 months)
Data Scientist
Itaú Unibanco
Nov 2019 - Jan 2020 (2 months)
Data Scientist / Computer Vision Engineer
- Developed computer vision projects for Itaú Unibanco, the largest bank in Latin America.
- Projects involved object detection in security images, signature detection/verification, document analysis, OCR, among others.
- The solutions were deployed to production, impacting millions of customers.
- Activities involved understanding project requirements and explaining complex concepts to non-technical people from different areas of the company.
- Projects involved object detection in security images, signature detection/verification, document analysis, OCR, among others.
- The solutions were deployed to production, impacting millions of customers.
- Activities involved understanding project requirements and explaining complex concepts to non-technical people from different areas of the company.
EPFL (École polytechnique fédérale de Lausanne)
Aug 2018 - Oct 2018 (2 months)
Summer Researcher
Add some compelling projects here to demonstrate your experience
Data Augmentation for Skin Lesion Analysis
Deep learning models show remarkable results in automated skin lesion analysis. However, these models demand considerable amounts of data, while the availability of annotated skin lesion images is often limited. Data augmentation can expand the training dataset by transforming input images. In this work, we investigate the impact of 13 data augmentation scenarios for melanoma classification trained on three CNNs (Inception-v4, ResNet, and DenseNet). Scenarios include traditional color and geometric transforms, and more unusual augmentations such as elastic transforms, random erasing and a novel augmentation that mixes different lesions. We also explore the use of data augmentation at test-time and the impact of data augmentation on various dataset sizes. Our results confirm the importance of data augmentation in both training and testing and show that it can lead to more performance gains than obtaining new images. The best scenario results in an AUC of 0.882 for melanoma classification without using external data, outperforming the top-ranked submission (0.874) for the ISIC Challenge 2017, which was trained with additional data.
ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection - Task 3 (Classification)
This section lets you add any degrees or diplomas you have earned.
Universidade Estadual de Campinas
Master of Science (MSc), Computer Engineering
Jan 2017 - Jan 2019
Master's thesis: Deep Learning for Skin Lesion Classification: Augment, Train, and Ensemble.
Universidade Estadual de Campinas
Engineer’s Degree (5-yr), Computer Engineering
Jan 2010 - Jan 2015
University of Sydney
Study Abroad, Computer Engineering
Jan 2013 - Jan 2014
Full fellowship by CNPq (Brazilian National Council for Scientific and Technological Development).
Courses taken:
Computational Methods for Life Sciences; Molecular Biology and Genetics; Electronic Devices and Circuits; Management for Engineers; Operating Systems and Machine Principles; Introduction to Artificial Intelligence; Digital Signal Processing; Object Oriented Design
Courses taken:
Computational Methods for Life Sciences; Molecular Biology and Genetics; Electronic Devices and Circuits; Management for Engineers; Operating Systems and Machine Principles; Introduction to Artificial Intelligence; Digital Signal Processing; Object Oriented Design