"Predicting the Computational Cost of Deep
Learning Models"

This paper provide the general guide to predict
the time it will take to train a deep learning network to solve
a given problem.

In this work the authors  have demonstrated a deep learning model
that is capable of accurately predicting the required execution
time for a wide range of the most frequently used components
of neural networks.

University of Michigan - Ann Arbor

- It requires very large amount of data in order to perform better than other techniques.

- It is extremely expensive to train due to complex data models. Moreover deep learning requires expensive GPUs and hundreds of machines. This increases cost to the users.

- There is no standard theory to guide you in selecting right deep learning tools as it requires knowledge of topology, training method and other parameters. As a result it is difficult to be adopted by less skilled people.

- It is not easy to comprehend output based on mere learning and requires classifiers to do so. Convolutional neural network based algorithms perform such tasks.

Drawbacks or disadvantages of Deep Learning

Predicting the Computational Cost of Deep
Learning Models

Deep learning model computational cost calculation

"Text Genre and Training Data Size in Human-Like Parsing" 

In the paper, the authors compare the performance of the deep learning model  the amount with different conditions of data. They demonstrated that the "right" quality of data determines the performance of dep learning. Their comparisons confirm that genre of data matters.

Learn Before

Related