Inventor · San Diego, CA, US

Eren BALEVI

20Patents
2h-index
22Co-inventors
49Inventor score

Filing activity: Oct 29, 2019 → Jan 18, 2024

Most-cited inventions

PatentTitleAreaCited byStatus
US11575544B2 Low resolution OFDM receivers via deep learning Electricity 3 Active
US11916754B2 Configuring a user equipment for machine learning Electricity 2 Active
US12126467B2 Low resolution OFDM receivers via deep learning Electricity 0 Active
US12432675B2 Signal synchronization for over-the-air aggregation in a federated learning framework Electricity 0 Active
US12255714B2 Techniques for encoding and decoding a channel between wireless communication devices Electricity 0 Active
US12127014B2 Protocol stack for analog communication in split architecture network for machine learning (ML) functions Electricity 0 Active
US12175346B2 Method and apparatus for fetching gradient data for federated learning process Electricity 0 Active
US12143299B2 Upper analog media access control (MAC-A) layer functions for analog transmission protocol stack Electricity 0 Active
US12355633B2 Configuring a user equipment for machine learning Electricity 0 Active
US11825553B2 UE capability for AI/ML Physics 0 Active
US11997693B2 Lower analog media access control (MAC-A) layer and physical layer (PHY-A) functions for analog transmission protocol stack Electricity 0 Active
US12035256B2 Power control in over the air aggregation for federated learning Electricity 0 Active
US12089291B2 Machine learning model configuration in wireless networks Physics 0 Active
US12261792B2 Group-common reference signal for over-the-air aggregation in federated learning Electricity 0 Active
US12035286B2 Gradient accumulation for federated learning Electricity 0 Active
US12041534B2 Network measurements for enhanced machine learning model training and inference Electricity 0 Active
US11818806B2 ML model training procedure Physics 0 Active
US11956785B2 User equipment participation indications associated with federated learning Physics 0 Active
US12401436B2 Gradient dropping for federated learning Electricity 0 Active
US12335035B2 Autoencoder-based error correction coding for low-resolution communication Electricity 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.