Posts

Hi there, I’m a PhD student in the School of Mathematics and Statistics at the University of Sydney (USYD), with my research in finding new ways to understand machine learning. I also teach at the USYD, and currently teaching/have taught: QBUS6810: Statistical Learning and Data Mining MATH1002: Linear Algebra MATH1023: Multivariable Calculus and Modelling MATH1011: Applications of Calculus MATH1013: Mathematical Modelling PHAR1812: Basic Pharmaceutical Sciences I graduated USYD with first class honors, with my research also in machine learning....

Abstract When training a neural network, vector data is input into a sequence of adjustable affine functions and nonlinear transformations. This process works well for visual data, and many other applications are currently being developed. However, little attention is paid to the abstract vector basis associated with a given data format. My research involves machine learning in a basis-independent way. In particular, I have found neural networks can be trained using a basis of discrete orthogonal Hanh polynomials....

Why PySoap While Tensorflow is the state of the art software for machine learning, it requires a heavy amount of hardware space to be installed. PySoap, primarily developed for my own research, is a light weight implementation of fully connected and convolutional neural networks. The only requirements are basic Python packages: Numpy, abc, inspect, and h5py. What is in PySoap PySoap, currently, implements Dense, Conv_2D, and BatchNorm layers. It also features many different optimizers such as Adam, SGD, Adagrad, etc....