GitHub

This repository is a Python research project for studying prediction-market efficiency and price discovery in the Los Angeles mayoral race using Kalshi and Polymarket data.

Kalshi official API for market metadata, candlesticks, trades, and order books. Polymarket official/public APIs for event metadata, markets, token IDs, price history, trades, and order books. Raw data ...
IEEE

Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study

Abstract: Some real-world domains, such as Agriculture and Healthcare, comprise early-stage disease indications whose recording constitutes a rare event, and yet, whose precise detection at that stage ...
IEEE

On Centralization and Unitization of Batch Normalization for Deep ReLU Neural Networks

Abstract: Batch normalization (BN) enhances the training of deep ReLU neural network with a composition of mean centering (centralization) and variance scaling (unitization). Despite the success of BN ...