Asked 29th Mar, 2020

Training Loss Vs Testing Loss (Machine and Deep Learning wise)?

Hey Colleagues,
I hope you are healthy and safe during this quarantine.
For any machine learning model, we evaluate the performance of the model based on several points, and the loss is amongst them. We all know that an ML model:
1- Underfits, when the training loss is way more significant than the testing loss.
2- Overfits, when the training loss is way smaller than the testing loss.
3- Performs very well when the training loss and the testing loss are very close.
My question is directed to the third point. I am running a DL model (1D CNN), and I have the following results: (Note that, my initial loss was 2.5)
- Training loss = 0.55
- Testing Loss = 0.65
Nevertheless, I am not quite sure if the results are acceptable. Since the training loss is a bit high (0.5). I tried to lower the training loss by giving more complexity to the model (Increasing the number of CNN layers and MLP layers); however, this is a very tricky process as whenever I increase the complexity of the architecture, the testing loss increases, and the model easily overfits.
Finally, to say that our model performed very well, should we get a low training loss (say less than 0.1) or my case is still considered good too?
I look forward to hearing from you,
Thanks and regards,

Most recent answer

8th Apr, 2020
Arbab Faisal
COMSATS University Islamabad Abbottabad Campus
You can add more data or try to reshuffle the existing data i.e., Make new training and testing sets.
1 Recommendation

All Answers (5)

29th Mar, 2020
Patrick Timmons
University College Dublin
That seems quite close really.
If you want to really get them closer, you could add a Dropout/SpatialDropout layer, which would help prevent overfitting.
2 Recommendations
30th Mar, 2020
Majdi Flah
The University of Western Ontario
Mohammed Deeb, I think that I will go more with adding more data since my data is quite limited.
Mah Parsa Does BELiMs work with Time Series?
1 Recommendation
Can you help by adding an answer?

Similar questions and discussions

Related Publications

Full-text available
Data Science and analysis is playing the most significant role today covering every industry in the market.For e.g finance,e-commerce,business,education,government. Now organizations play a 360 degree role to analyzed the behavior and interest of their customers to take decisions in favour of them.Data is analyzed through programming language such...
Full-text available
Python has become the programming language of choice for research and industry projects related to data science, machine learning, and deep learning. Since optimization is an inherent part of these research fields, more optimization related frameworks have arisen in the past few years. Only a few of them support optimization of multiple conflicting...
Full-text available
Certificate of completion for "Machine Learning, Data Science and Deep Learning with Python".
Got a technical question?
Get high-quality answers from experts.