Answer-first summary for fast verification
Answer: Hyperparameter tuning
The correct answer is **C. Hyperparameter tuning**. This process involves adjusting the configuration variables that directly influence the training process, such as learning rate, number of hidden layers, and nodes selection, to optimize model performance within the given constraints. - **A. Cross Validation** is incorrect because it pertains to the method of partitioning data into training, validation, and test sets to evaluate model performance. - **B. Regularization** is incorrect as it refers to techniques used to prevent overfitting by adding a penalty to the loss function. - **D. Drift detection management** is incorrect because it involves monitoring and adjusting the model in response to changes in the underlying data distribution over time. For further reading, refer to: - [Vertex AI Hyperparameter Tuning Overview](https://cloud.google.com/vertex-ai/docs/training/hyperparameter-tuning-overview) - [Hyperparameter Tuning with Bayesian Optimization](https://cloud.google.com/blog/products/ai-machine-learning/hyperparameter-tuning-cloud-machine-learning-engine-using-bayesian-optimization)
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
As a junior Data Scientist at a retail company, you are tasked with developing a deep neural network model using TensorFlow to enhance customer satisfaction for after-sales services. Your model's performance is suboptimal due to challenges in selecting appropriate learning rates, the number of hidden layers, and nodes, which are crucial for achieving fast convergence without overfitting. The project has tight constraints on computational resources and requires the model to be deployed in a cost-effective manner. In the context of machine learning, what is this optimization challenge known as? Choose the BEST option.
A
Cross Validation
B
Regularization
C
Hyperparameter tuning
D
Drift detection management
No comments yet.