SPPU · Final Year Artificial Intelligence and Data Science · 2020 Course
Distributed Computing
417531 · Semester VIII · 3 credits · In-semester 30 + end-semester 70
Unit 1: Introduction to Distributed Computing
6 hoursCharacteristics, goals and types; system models; AI and data science on distributed systems: storage, consistency, communication, synchronisation and fault tolerance; use cases.
Marks: 15 in the in-semester exam
- Distributed system models
- AI and data science in distributed systems
Unit 2: Distributed Data Management
6 hoursParallel and distributed models; message passing; HDFS and GFS; cloud clusters; message brokers, stream processing and edge computing; eager, lazy, quorum and consensus replication; consistency models; DHTs and distributed indexing.
Marks: 15 in the in-semester exam
- HDFS and GFS
- Replication strategies
- Consistency models
- Distributed hash tables
Unit 3: Distributed Algorithms
6 hoursCoordination; consensus with Paxos, Raft, ZAB and viewstamped replication; fault tolerance; load balancing strategies; ML, RL, GA and swarm methods for resource allocation and scheduling.
Marks: 17–18 in the end-semester exam
- Paxos and Raft consensus
- Fault tolerance and recovery
- Load balancing strategies
- AI for distributed resource allocation
Unit 4: Distributed Machine Learning
6 hoursData and model parallelism; distributed gradient descent; federated learning; all-reduce, Hogwild and elastic averaging SGD; Spark, TensorFlow and Petuum; AI for resource management and anomaly detection.
Marks: 17–18 in the end-semester exam
- Data and model parallelism
- Distributed gradient descent
- Federated learning
- Distributed ML frameworks
Unit 5: Big Data Processing
6 hoursHadoop, Spark, Storm, Samza and Flink; SISD to MIMD, SPMD and MPP; scalable ingestion; real-time and streaming analytics.
Marks: 17–18 in the end-semester exam
- Big data processing frameworks
- Data ingestion
- Real-time and streaming analytics
Unit 6: Security and Privacy
6 hoursInsider threats; TLS, PKI and VPNs; differential privacy, homomorphic encryption and SMPC; anonymisation; AI-based intrusion detection and UEBA.
Marks: 17–18 in the end-semester exam
- Secure communication: TLS and PKI
- Differential privacy and homomorphic encryption
- AI-based intrusion detection
Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.