Drop-Connect as a Fault-Tolerance Approach for RRAM-based Deep Neural Network Accelerators.
Mingyuan XiangXuhan XiePedro SavareseXin YuanMichael MaireYanjing LiPublished in: CoRR (2024)
Keyphrases
- fault tolerance
- neural network
- fault tolerant
- load balancing
- response time
- distributed computing
- high availability
- peer to peer
- distributed systems
- fault management
- mobile agents
- group communication
- artificial neural networks
- replicated databases
- high scalability
- high performance computing
- database replication
- failure recovery
- single point of failure
- computing systems
- error detection
- expert systems
- cooperative
- data sets
- metadata