Machine Learning
Artificial intelligence is becoming increasingly powerful and useful thanks to advancements in machine learning that have made the technologies more accessible and relevant to solving problems. Some of the applications have been outstanding thanks to the amazing pattern recognition abilities, and have helped reach new levels of accuracy and simplicity in what used to be difficult problems.
The field became interesting to me back in early 2015 when I started reading about deep learning, a field that was just beginning to come into fruition due to some big breakthroughs in fields like HPC and neural network design.
The interest led into my self-tailored third and final year projects, where I was fortunate enough to work closely with my university department to try out the field with undergraduate students. Furthermore, the first project was a great success and helped make deep learning become one of the most popular final year project topics.
For my third year project in 2015, I wanted to explore machine learning through application to a real world problem. Facial Keypoints Problem The facial keypoints problem stems from a branch of computer vision for detecting point of interest locations. A competition was standardised at kaggle.com as the ‘Kaggle Facial Keypoints Challenge‘, benchmarking researchers from … Continue reading Facial Keypoint Detection
In my final (fourth) year project module, I decided to continue in my interest of machine learning, but this time recurrent models. Recurrent models tackle sequence problems including fields like natural language processing, computer vision and healthcare. Model There are many different recurrent models out there, the most popular being LSTMs. In my work I … Continue reading Recurrent Neural Networks – Differential Neural Computers