We introduce the logical grammar emdebbing (LGE), a model inspired by
pr...
We use a binary attribute representation (BAR) model to describe a data ...
We implement a divide-and-concur iterative projection approach to
contex...
Iterative projection methods may become trapped at non-solutions when th...
Recent experiments by Springer and Kenyon have shown that a deep neural
...
We explore a new approach for training neural networks where all loss
fu...
We introduce a new neural network model, together with a tractable and
m...
We introduce a new neural network model, together with a tractable and
m...
We study neural networks whose only non-linear components are multiplier...
We describe how the powerful "Divide and Concur" algorithm for constrain...