After learning computer programming through a desire to make video games, I decided to study computational neuroscience and machine-learning at Caltech to explore the link between computer programs and the mind. I was fascinated by the potential link of neural networks and the functioning of the brain, but I knew that much deeper insights could be gained by studying real neurons and neural networks. As a graduate student at UCSD, I performed voltage-sensitive dye imaging experiments of a simple biological neural circuit, the leech ganglion. My hope was that the ability to see a significant fraction of all neural activity at once in a simple nervous system would lead to a complete model and understanding. However, I learned that even the most “simple” nervous systems are far more complex than we have really yet to appreciate. My research now focuses on attempting to grasp this complexity and bring insights from modern neuroscience into machine-learning.