Learning

7812 Paths · page 359 / 782

• Federated Learning: Distributed, Privacy-Sensitive Model Trainingactive

  This advanced path equips machine learning practitioners with the knowledge to design and implement federated learning systems. It covers core algorithms, communication efficiency, privacy-preserving techniques, and secure aggregation, grounded in necessary prerequisites in distributed systems and privacy fundamentals.

  id: 4241slug: clp-1788630672023-we36irupdated: 2026-09-07

• Identifying and Mitigating Bias in Machine Learning Systemsactive

  This advanced graduate-level path equips ML practitioners with the knowledge and skills to systematically identify, measure, and mitigate bias in machine learning systems. It covers fairness metrics, bias detection techniques, fairness constraints, algorithmic fairness frameworks, and privacy-preserving ML, with a strong foundation in ethics and law.

  id: 4240slug: clp-1788630655943-icu806updated: 2026-09-07

• Applying Machine Learning to Robotic Perception and Controlactive

  This advanced graduate-level path equips roboticists with the knowledge to apply machine learning to robotic perception and control. It covers core ML concepts, robot perception, learning-based control, and specialized topics like imitation learning, manipulation, and navigation, culminating in a capstone integration project.

  id: 4239slug: clp-1788630642072-f6k271updated: 2026-09-07

• Attention-Based Architectures and Transformersactive

  A comprehensive graduate-level learning path covering attention mechanisms, transformer architectures, and their applications in NLP and vision. Starting from foundational deep learning concepts, the path progresses through self-attention, multi-head attention, the transformer encoder-decoder, and major variants such as BERT, GPT, and vision transformers, with practical implementation exercises.

  id: 4238slug: clp-1788630623906-jng7u4updated: 2026-09-07

• Generative Modeling for Data Synthesisactive

  A comprehensive graduate-level path to master generative modeling, covering the mathematical foundations, core families (GANs, VAEs, normalizing flows, diffusion, autoregressive), and practical techniques for image and text generation. Designed for ML practitioners seeking systematic depth.

  id: 4237slug: clp-1788630607495-6d5z1jupdated: 2026-09-07

• Learning to Learn: Foundations and Algorithms for Fast Adaptationactive

  This path equips machine learning practitioners with a systematic understanding of meta-learning, enabling them to design and apply algorithms that learn new tasks quickly. It covers the core concepts, algorithms, and practical skills needed to build models that adapt efficiently to novel tasks.

  id: 4236slug: clp-1788630585459-6f8cqlupdated: 2026-09-07

• Scaling Machine Learning Algorithms for Large Datasetsactive

  A comprehensive graduate-level learning path for ML engineers to systematically scale machine learning algorithms from single-machine to distributed environments. It covers fundamental scalability concepts, distributed computing frameworks, parallel and online learning techniques, and large-scale inference, culminating in a capstone project.

  id: 4235slug: clp-1788630565194-sjmc97updated: 2026-09-07

• Model Compression and Optimization for Edge Deploymentactive

  This advanced learning path equips ML engineers with the knowledge and skills to compress and optimize deep learning models for deployment on resource-constrained edge devices. It covers fundamental compression techniques including pruning, quantization, and knowledge distillation, as well as practical deployment workflows using ONNX and TensorRT. The path emphasizes hands-on application and real-world considerations for mobile and embedded platforms.

  id: 4234slug: clp-1788630541833-ozxacuupdated: 2026-09-07

• Machine Learning for Healthcare and Medical Dataactive

  A comprehensive learning path for healthcare ML practitioners to apply machine learning to medical data, covering essential clinical concepts, data handling, model development, evaluation, and regulatory considerations. Designed for graduate-level learners with prior ML experience.

  id: 4233slug: clp-1788630520957-a0tmylupdated: 2026-09-07

• Machine Learning for Finance and Tradingactive

  This advanced graduate-level path equips quants and financial ML practitioners with the skills to apply machine learning to financial data and trading. It covers financial time series analysis, risk prediction, fraud detection, algorithmic trading, portfolio optimization, and valuation models, emphasizing rigorous validation and practical implementation.

  id: 4232slug: clp-1788630505065-47b6cvupdated: 2026-09-07