hitashu Goto Github PK

100-days-of-nlp

arima_sample

basic-ds-and-ml

data science and machine learning

bipartite-network-of-food-nlp

casualml

causalml

A course on causal machine learning.

chest-xray-predictions

Pneumonia is a very common disease. It can be either: 1) Bacterial pneumonia 2) Viral Pneumonia 3) Mycoplasma pneumonia and 4) Fungal pneumonia. This dataset consists pneumonia samples belonging to the first two classes. The dataset consists of only very few samples and that too unbalanced. The aim of this kernel is to develop a robust deep learning model from scratch on this limited amount of data. We all know that deep learning models are data hungry but if you know how things work, you can build good models even with a limited amount of data

combining-batch-normalization-and-dropout-in-the-training-of-deep-neural-network

The original work that we have tried to replicate was done by a team of researchers from Tencent Technology, the Chinese University of Hong Kong, and Nankai University who proposed a novel method to address the issue of improving training deep neural networks (DNN). Their work is published through the paper "Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks" (Chen et al., 2019) which proposes a marriage of 2 commonly used techniques – Batch Normalisation and Dropout, to achieve input whitening that neither method could otherwise achieve independently.

creditcardfraud2

cs6120_hk_fa

fraud-prediction

guides

A collection of easy-to-understand guides to programming tools

idmp

info-viz

Capstone Project [Walmart Sales Forecasting]

lendingclub-data_credit-risk-analysis

machine-learning

Creating a repository of all ML projects done over time for learning purposes

merger_and_acquisition_prediction

mlfromscratch

Machine Learning algorithm implementations from scratch.

multiclass-classification-on-human-activity-dataset

Automatic activity recognition systems aim to capture the state of the user and its environment by exploiting heterogeneous sensors, and permit continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in healthcare applications, for automatic and intelligent daily activity monitoring for elderly people. The Human Activity Recognition database was built from the recordings of 30 study participants performing activities of daily living (ADL) while carrying a waist-mounted smartphone with embedded inertial sensors. The objective is to classify activities into one of the six activities performed.

python-fun

Some fun and useful projects with Python

python_for_microscopists

https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1

s-p-500-stock-analysis-and-predictions

search_optimization_for_clinical_trial_records

Enhanced search results of clinical trial records based on user query utilizing taxonomy of Medical SubHeadings by providing keywords and document recommendations. Dataset was taken from clinicaltrials.gov

stock-prediction-models

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations