8000 matthewweaver (Matthew Weaver) · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View matthewweaver's full-sized avatar

Block or report matthewweaver

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
matthewweaver/README.md

Portfolio

Completed Courses



Machine Learning


Deep Learning


Reinforcement Learning


Generative Adversarial Networks
Supervised Learning
-- Linear Regression
-- Logistic Regression
-- Cost Function
-- Gradient Descent
-- Model Representation
-- Jupyter
-- Feature Engineering
-- Feature Scaling
-- Multi Variable Linear Regression
-- Vectorisation
-- SKLearn
-- Classification
-- Logistic Cost Function
-- Decision Boundary
-- Logistic Gradient Descent
-- Logistic Loss
-- Overfitting
-- Regularisation
-- Sigmoid

Advanced Learning Algorithms
-- Neural Networks for Binary Classification
-- Neural Networks for Multiclass Classification
-- Appling Machine Learning
-- Decision Trees
-- Coffee Roasting Case Study - Numpy
-- Coffee Roasting Case Study - Tensorflow
-- Neurons and Layers
-- Multiclass Tensorflow
-- Relu
-- Softmax
-- Bias and Variance
-- Model Evaluation
-- Information Gain
-- Tree Ensembles

Unsupervised Learning
-- Anomaly Detection
-- K Means Clustering
-- Collaborative Filtering Recommender
-- Content Based Filtering Recommender
-- Deep Q Learning
-- Principal Component Analysis
Neural Networks
-- Numpy
-- Logistic Regression
-- Planar Data Classification
-- Deep Neural Network
-- Image Classification

Hyperparameter tuning, Regularization and Optimization
-- Initialisation
-- Regularisation
-- Gradient Checking
-- Optimisation
-- Tensorflow

Convolutional Neural Networks
-- Convolutional Model
-- Convolutional Application
-- Residual Networks
-- Transfer Learning
-- Car Detection with YOLO
-- Image Segmentation with U-Net
-- Face Detection
-- Neural Style Transfer

Sequence Models
-- Recurrent Neural Network
-- Character Level Language Model
-- Long Short Term Memory
-- Word Vectors
-- Emojify
-- Neural Machine Translation
-- Trigger Word Detection
-- Transformers Network
-- Transformer Pre-Processing
-- Transformer Named Entity Recognition
-- Transformer Question Answering
Fundamentals
-- Bandits and Exploration-Exploitation
-- Dynamic Programming

Sample Based Learning Methods
-- Blackjack
-- Temporal Difference
-- Q Learning and Expected Sarsa
-- Dyna Q

Prediction and Control with Function Approximation
-- Semi Gradient TD with State Aggregation
-- Semi Gradient TD with Neural Network
-- Function Approximation and Control
-- Actor-Critic

A Complete Reinforcement Learning System (Capstone)
-- Case Study
-- Lunar Landing Agent
-- Parameter Study
Build Basic GANs
-- PyTorch
-- Basic GAN
-- Deep Convolutional GAN
-- Wasserstein GAN
-- Conditional GAN
-- Controllable Generation
-- InfoGAN
-- ProteinGAN
-- Spectrally Normalised GAN
-- Video Generation TGAN

Build Better GANs
-- Frechet Inception Distance
-- Bias
-- StyleGAN
-- StyleGAN2
-- BigGAN
-- GAN Debiasing
-- Neural Radiance Fields
-- Perceptual Path Length
-- Score Based Generative Modelling
-- Variational Autoencoder

Apply GANs
-- Data Augmentation
-- UNet
-- Pix2Pix
-- Pix2PixHD
-- CycleGAN
-- CycleGAN Generator
-- CycleGAN Consistency Loss
-- GauGAN
-- Generative Teaching Networks
-- MUNIT






Projects

Garnet - Generative Adversarial Reinforcement Network Exploitation Tool
Combining a GAN with a Deep Reinforcement Learning agent to produce novel ideas for penetration testing, which the agent implements and gets feedback.

Scalable Streaming Data Platform
A web app written in Python with Flask allows input of search terms; a Scala app on Flink ingests matching tweets into Kafka in real time; a Python sentiment analysis model on Flink adds feature to tweet; Kubernetes deploys all services either locally with Minikube or AWS hosted with EKS; Kafka Connect indexes data with Elasticsearch and visualises on a Kibana dashboard allowing searching/aggregation and displays sentiment on a map

House Prices Application
Python app to search properties on Zoopla’s API; ingest historical house price data; calculate transport times using Google Maps API; crawl the Zoopla website for additional search and filter capabilities; applied regression models and a neural net to predict house values and compare to asking price\



Books

Deep Learning Artificial Intelligence: A Modern Approach Fluent Python Designing Data-Intensive Applications Scala for the Impatient

and more technical books and non-technical books about data and AI

Popular repositories Loading

  1. house-prices house-prices Public

    Jupyter Notebook 12 1

  2. scalable-streaming-data-platform scalable-streaming-data-platform Public

    Java 2

  3. zoopla zoopla Public

    Forked from AnthonyBloomer/zoopla

    An API to allow developers to create applications using hyper local data on 27m homes, over 1m sale and rental listings, and 15 years of sold price data in the UK.

    Python 1

  4. coursera-machine-learning-labs coursera-machine-learning-labs Public

    Jupyter Notebook 1

  5. coursera-deep-learning-labs coursera-deep-learning-labs Public

    Jupyter Notebook 1

  6. kubernetes kubernetes Public

    Java

0