AWS Certified Machine Learning - Specialty (MLS-C01) Flashcards¶
30 cards from this guide's fact sheet and notes. Click a question to reveal the answer.
To study with spaced repetition, download flashcards.csv and import it into Anki or Quizlet (comma separated, first row is the header). Back to the study guide.
Ml algorithms evaluation¶
Binary Classification (ml algorithms evaluation)
Linear Learner, XGBoost, Neural Networks
Multi-class Classification (ml algorithms evaluation)
XGBoost, Image Classification, BlazingText
Regression (ml algorithms evaluation)
Linear Learner, XGBoost, Neural Networks
Anomaly Detection (ml algorithms evaluation)
Random Cut Forest, IP Insights
Time Series (ml algorithms evaluation)
DeepAR, Amazon Forecast
NLP (ml algorithms evaluation)
BlazingText, Sequence2Sequence, Comprehend
Computer Vision (ml algorithms evaluation)
Image Classification, Object Detection, Rekognition
Structured/Tabular (ml algorithms evaluation)
XGBoost, Linear Learner
Images (ml algorithms evaluation)
Image Classification, Object Detection
Text (ml algorithms evaluation)
BlazingText, Comprehend
High-dimensional (ml algorithms evaluation)
PCA first, then other algorithms
Sparse data (ml algorithms evaluation)
Linear Learner, Factorization Machines
Fast training (ml algorithms evaluation)
Linear Learner, K-Means
High accuracy (ml algorithms evaluation)
XGBoost, Deep Learning
Interpretability (ml algorithms evaluation)
Linear Learner, Decision Trees
Scalability (ml algorithms evaluation)
Built-in algorithms, distributed training
Imbalanced data (ml algorithms evaluation)
Precision, Recall, F1, AUC
Business cost of errors (ml algorithms evaluation)
Weighted precision/recall
Ranking (ml algorithms evaluation)
AUC, Average Precision
Ml comprehensive notes¶
XGBoost (ml comprehensive notes)
General-purpose classification/regression
Linear Learner (ml comprehensive notes)
Linear relationships, sparse data
DeepAR (ml comprehensive notes)
Time series forecasting
Image Classification (ml comprehensive notes)
Computer vision tasks
BlazingText (ml comprehensive notes)
Text classification, word embeddings
K-Means (ml comprehensive notes)
Clustering, data segmentation
PCA (ml comprehensive notes)
Dimensionality reduction
Random Cut Forest (ml comprehensive notes)
Anomaly detection
Training (ml comprehensive notes)
ml.p3 (GPU) for deep learning, ml.m5 for general ML
Inference (ml comprehensive notes)
ml.m5 for CPU, ml.g4dn for GPU, ml.inf1 for cost-effective inference
Processing (ml comprehensive notes)
ml.m5 or ml.c5 for data processing