BecomeAllan
Undergraduate statistics student at the University of Brasília (UnB, Brazil) who loves math, code, and how the brain works.
Brazil
Pinned Repositories
aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
argo-scholar
Literature Review Made Easy with Visualization
ce089
Repositório da disciplina ce089 - Estatística Computacional II
JsonFlow
JsonFlow is a minimal library for building frameworks to handle JSON/Dict data as APIs in pure Python to empower any application.
ML-SLRC
Research project for automating systematic literature reviews. Best Paper Award of WEBIST 2022
RNN
Resumo sobre o comportamento de RNN do básico a aplicações básicas sobre sua funcionalidade.
S2Query
S2query is a library to search papers from Semantic Scholar.
webportfolio
This is my personal web page
NLP-MCTI-PPF
Natural Language Processing (NLP) applied to the Research Finantial Products Portfolio (PPF) of the Brazilian Ministry of Science, Technology and Innovations (MCTI)
BecomeAllan's Repositories
BecomeAllan/S2Query
S2query is a library to search papers from Semantic Scholar.
BecomeAllan/ce089
Repositório da disciplina ce089 - Estatística Computacional II
BecomeAllan/JsonFlow
JsonFlow is a minimal library for building frameworks to handle JSON/Dict data as APIs in pure Python to empower any application.
BecomeAllan/ML-SLRC
Research project for automating systematic literature reviews. Best Paper Award of WEBIST 2022
BecomeAllan/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
BecomeAllan/annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
BecomeAllan/argo-scholar
Literature Review Made Easy with Visualization
BecomeAllan/ARL_trab
Trabalho de Regressao
BecomeAllan/DeepOptimization
BecomeAllan/dsdeliver
Projeto da semana do devsuperior2.0
BecomeAllan/EvalAI-Starters
How to create a challenge on EvalAI?
BecomeAllan/markdown-preview-enhanced
One of the 'BEST' markdown preview extensions for Atom editor!
BecomeAllan/RNN
Resumo sobre o comportamento de RNN do básico a aplicações básicas sobre sua funcionalidade.
BecomeAllan/webportfolio
This is my personal web page
BecomeAllan/control-engineering-with-python
Control Engineering with Python
BecomeAllan/Grounded-Segment-Anything
Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
BecomeAllan/intelligent-app-from-videos-google-generativeai-neo4j
BecomeAllan/MAGALI
MAGALI: An AI-powered tool to analyze nutrients and carbs from food photos, aiding metabolic health optimization.
BecomeAllan/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
BecomeAllan/neurosymbolic-representations-for-IR
Resources for Tutorial on Neuro-Symbolic Representations for IR
BecomeAllan/Non-linear-system
Nonlinear problem solving written in R.
BecomeAllan/portuguese-bert
Portuguese pre-trained BERT models
BecomeAllan/quarto-actions
BecomeAllan/Semi-automation-of-systematic-review-of-clinical-trials-in-medical-psychology-with-BERT-models
We employed pre-trained BERT models (distillBERT, BioBert, and SciBert) for text-classifications of the titles and abstracts of clinical trials in medical psychology. The average score of AUC is 0.92. A stacked model was then built by featuring the probability predicted by distillBERT and keywords of search domains. The AUC improved to 0.96 with F1, precision, and recall increasing to 0.95, 0.94, and 0.96 respectively. Training sample size of 100 results in the most cost-effective performance.
BecomeAllan/Spiral
BecomeAllan/systematic-review-datasets
A collection of fully labeled systematic review datasets (title-abstract screening)
BecomeAllan/tamplate_paper
BecomeAllan/tokyo
BSPWM - Aesthetic Dotfiles 🍚
BecomeAllan/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
BecomeAllan/wanda
A simple and effective LLM pruning approach.