MSc-Thesis

Module: Masters Research Thesis

Language: Python

Grade: 75

Title: An investigation of supervised classification of therapeutic process from text.

Description: Refining basic and advanced machine learning algorithms including MLPC neural nets, fine-tuned with grid-searching, to apply therapeutic process labels to therapist-patient transcribed conversation turns. This project aimed to run controls without data augmentation but then, crucially, implement varying level of data augmentation (30, 60 and 90% increased data) in addition to combining techniques, to assess whether it improves the outcome of the estimations. This project found novel and profound results not limited to those which will shape the future of all research in this field.

Contents: Code, Written report. NOTE* The code provided will not be in it's final form. Much testing was done after the 12,000 data points were collected and so it's advised you first read the other ReadMe in this repo and feel free to DM me with any queries.

Supervised Classification from Text (P)

Related tags

Overview

MSc-Thesis

Owner

Matthew Laws

The Python3 import playground

A tiny, friendly, strong baseline code for Person-reID (based on pytorch).

Code for all the Advent of Code'21 challenges mostly written in python

A Simplied Framework of GAN Inversion

Unofficial JAX implementations of Deep Learning models

A repository for the updated version of CoinRun used to collect MUGEN, a multimodal video-audio-text dataset.

Yolo Traffic Light Detection With Python

Official implementation of Sparse Transformer-based Action Recognition

Deep generative modeling for time-stamped heterogeneous data, enabling high-fidelity models for a large variety of spatio-temporal domains.

Reproduces the results of the paper "Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations".

MoveNet Single Pose on DepthAI

The devkit of the nuScenes dataset.

Segcache: a memory-efficient and scalable in-memory key-value cache for small objects

"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback"

Learning Visual Words for Weakly-Supervised Semantic Segmentation

Object Database for Super Mario Galaxy 1/2.

Deploying PyTorch Model to Production with FastAPI in CUDA-supported Docker

CLADE - Efficient Semantic Image Synthesis via Class-Adaptive Normalization (TPAMI 2021)

Spherical Confidence Learning for Face Recognition, accepted to CVPR2021.

Supervised forecasting of sequential data in Python.