Erlanson, Ruth
Analog Neural Networks as Decoders
Erlanson, Ruth, Abu-Mostafa, Yaser
In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By interconnecting such KWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of interconnected KWTA networks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.
Analog Neural Networks as Decoders
Erlanson, Ruth, Abu-Mostafa, Yaser
In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By interconnecting suchKWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of interconnected KWTAnetworks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.
Analog Neural Networks as Decoders
Erlanson, Ruth, Abu-Mostafa, Yaser
In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By interconnecting such KWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of interconnected KWTA networks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.
On the K-Winners-Take-All Network
Majani, E., Erlanson, Ruth, Abu-Mostafa, Yaser S.
We present and rigorously analyze a generalization of the Winner Take-All Network: the K-Winners-Take-All Network.
On the K-Winners-Take-All Network
Majani, E., Erlanson, Ruth, Abu-Mostafa, Yaser S.
We present and rigorously analyze a generalization of the Winner Take-All Network: the K-Winners-Take-All Network. This network identifies the K largest of a set of N real numbers. The network model used is the continuous Hopfield model.