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

A collection of random and hastily hacked together scripts for investigating EU-DCC

LSUN Dataset Documentation and Demo Code

TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.

MLSpace: Hassle-free machine learning & deep learning development

AAAI 2022 paper - Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

Contrastive Learning for Metagenomic Binning

Official implementation for "Low-light Image Enhancement via Breaking Down the Darkness"

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and reinforcement learning

Pytorch implementation of the paper SPICE: Semantic Pseudo-labeling for Image Clustering

Repository for reproducing `Model-Based Robust Deep Learning`

Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data

Tiny Kinetics-400 for test

A Keras implementation of CapsNet in the paper: Sara Sabour, Nicholas Frosst, Geoffrey E Hinton. Dynamic Routing Between Capsules

Implementation of UNET architecture for Image Segmentation.

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

Yoloxkeypointsegment - An anchor-free version of YOLO, with a simpler design but better performance

[CoRL 2021] A robotics benchmark for cross-embodiment imitation.

Decensoring Hentai with Deep Neural Networks. Formerly named DeepMindBreak.