Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision.
Florian GeisslerSyed QutubSayanta RoychowdhuryAli AsgariYang PengAkash DhamasiaRalf GraefeKarthik PattabiramanMichael PaulitschPublished in: AISafety@IJCAI (2021)
Keyphrases
- fault tolerance
- fault tolerant
- convolutional neural networks
- load balancing
- distributed computing
- distributed systems
- error detection
- peer to peer
- database replication
- replicated databases
- group communication
- high availability
- single point of failure
- response time
- mobile agents
- failure recovery
- high performance computing
- fault management
- cooperative
- data sets
- high scalability
- convolutional network
- massively parallel
- computer systems
- multi agent
- metadata
- databases