Searching CertSprout…
Searching CertSprout…
A little curiosity goes a long way
Search certifications, learning topics, career paths, public profiles and help across CertSprout.
Showing 20 results · Page 4 for “valuation”. More results are available below.
COASP · Generative AI systems
… assistant invents a plausible policy citation. Which evaluation concern is illustrated? Hallucination or unsupported generation Fluent output may lack factual support. Citation and groundin…
COASP · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
CRAGE · Generative AI systems
… assistant invents a plausible policy citation. Which evaluation concern is illustrated? Hallucination or unsupported generation Fluent output may lack factual support. Citation and groundin…
CRAGE · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
DBX-CTX · Generative AI systems
… assistant invents a plausible policy citation. Which evaluation concern is illustrated? Hallucination or unsupported generation Fluent output may lack factual support. Citation and groundin…
DBX-CTX · Machine-learning engineering
…te training data. Reproduce the serving inputs during evaluation. An unusually strong score deserves investigation if it collapses on genuinely unseen conditions. Worked example A time-serie…
DBX-CTX · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
DBX-GAI · Generative AI systems
… assistant invents a plausible policy citation. Which evaluation concern is illustrated? Hallucination or unsupported generation Fluent output may lack factual support. Citation and groundin…
DBX-GAI · Machine-learning engineering
…te training data. Reproduce the serving inputs during evaluation. An unusually strong score deserves investigation if it collapses on genuinely unseen conditions. Worked example A time-serie…
DBX-GAI · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
DBX-MLA · Generative AI systems
… assistant invents a plausible policy citation. Which evaluation concern is illustrated? Hallucination or unsupported generation Fluent output may lack factual support. Citation and groundin…
DBX-MLA · Machine-learning engineering
…te training data. Reproduce the serving inputs during evaluation. An unusually strong score deserves investigation if it collapses on genuinely unseen conditions. Worked example A time-serie…
DBX-MLA · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
DBX-MLP · Generative AI systems
… assistant invents a plausible policy citation. Which evaluation concern is illustrated? Hallucination or unsupported generation Fluent output may lack factual support. Citation and groundin…
DBX-MLP · Machine-learning engineering
…te training data. Reproduce the serving inputs during evaluation. An unusually strong score deserves investigation if it collapses on genuinely unseen conditions. Worked example A time-serie…
DBX-MLP · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
DP-100 · Azure machine learning workflow
…eriment needs reproducible data, code, parameters and evaluation results. Keep training and evaluation data appropriately separate to avoid leakage. Deployment adds another responsibility: m…
DP-100 · Machine-learning engineering
…te training data. Reproduce the serving inputs during evaluation. An unusually strong score deserves investigation if it collapses on genuinely unseen conditions. Worked example A time-serie…
DP-750 · Machine-learning engineering
…te training data. Reproduce the serving inputs during evaluation. An unusually strong score deserves investigation if it collapses on genuinely unseen conditions. Worked example A time-serie…
DP-750 · Responsible AI evaluation
…r release through monitoring and feedback; a one-time evaluation cannot capture every change in data or use. Worked example A model's overall accuracy is high but one user group has many mor…
People search uses public names, handles and headlines. Private and unlisted profiles are excluded. Your goals are visible only to you in search.