Valid Professional-Machine-Learning-Engineer Dumps shared by ExamDiscuss.com for Helping Passing Professional-Machine-Learning-Engineer Exam! ExamDiscuss.com now offer the newest Professional-Machine-Learning-Engineer exam dumps, the ExamDiscuss.com Professional-Machine-Learning-Engineer exam questions have been updated and answers have been corrected get the newest ExamDiscuss.com Professional-Machine-Learning-Engineer dumps with Test Engine here:
You have trained a DNN regressor with TensorFlow to predict housing prices using a set of predictive features. Your default precision is tf.float64, and you use a standard TensorFlow estimator; estimator = tf.estimator.DNNRegressor( feature_columns=[YOUR_LIST_OF_FEATURES], hidden_units-[1024, 512, 256], dropout=None) Your model performs well, but Just before deploying it to production, you discover that your current serving latency is 10ms @ 90 percentile and you currently serve on CPUs. Your production requirements expect a model latency of 8ms @ 90 percentile. You are willing to accept a small decrease in performance in order to reach the latency requirement Therefore your plan is to improve latency while evaluating how much the model's prediction decreases. What should you first try to quickly lower the serving latency?
Correct Answer: D
* Quantization is a technique that reduces the numerical precision of the weights and activations of a neural network, which can improve the inference speed and reduce the memory footprint of the model1. * Reducing the floating point precision from tf.float64 to tf.float16 can potentially halve the latency and * memory usage of the model, while having minimal impact on the accuracy2. * Increasing the dropout rate to 0.8 in either mode would not affect the latency, but would likely degrade the performance of the model significantly, as dropout is a regularization technique that randomly drops out units during training to prevent overfitting3. * Switching from CPU to GPU serving may or may not improve the latency, depending on the hardware specifications and the model complexity, but it would also incur additional costs and complexity for deployment4