In this paper I demonstrate a novel design for an optoelectronic State Machine which replaces input/output forming logic found in conventional state machines with BDD based optical logic while still using solid state memory in the form of flip-flops in order to store states. This type of logic makes use of waveguides and ring resonators to create binary switches. These switches in turn can be used to create combinational logic which can be used as input/output forming logic for a state machine. Replacing conventional combinational logic with BDD based optical logic allows for a faster range of state machines that can certainly outperform conventional state machines as propagation delays within the logic described are in the order of picoseconds as opposed to nanoseconds in digital logic.
This electronic document is a “live” template and already defines the components of your paper [title, text, heads, etc.] in its style sheet. CRITICAL: Do Not Use Symbols, Special Characters, or Math in Paper Title or Abstract.
Deep learning is a fast growing field in tech that is often described to have limitless potential. This paper describes its history, why the explosion in popularity, and how it works. An example of classifying images of handwritten digits (MNIST) will be explored using a fully connected network and a convolutional neural network. Next, a brief description of the tools necessary for the reader to implement his or her own network. Finally, a view of the state of the art being developed by companies such as Google, Facebook, and Baidu.