Pre-trained Models vs Training From Scratch

Developers should learn and use pre-trained models when building AI applications with limited data, time, or computational power, as they provide a strong starting point that can be customized for specific needs meets developers should use training from scratch when working with highly specialized or novel datasets where pre-trained models are unavailable or ineffective, such as in niche scientific research or custom industrial applications. Here's our take.

Pre-trained Models

Nice Pick

Developers should learn and use pre-trained models when building AI applications with limited data, time, or computational power, as they provide a strong starting point that can be customized for specific needs

Pros

• They are essential in domains like NLP for tasks such as sentiment analysis or chatbots using models like BERT, and in computer vision for object detection or image classification using models like ResNet
• Related to: transfer-learning, machine-learning

Cons

• Specific tradeoffs depend on your use case

Training From Scratch

Developers should use training from scratch when working with highly specialized or novel datasets where pre-trained models are unavailable or ineffective, such as in niche scientific research or custom industrial applications

Pros

• It is also appropriate when computational resources are sufficient and the goal is to avoid biases or limitations from pre-trained models, ensuring the model is tailored specifically to the task at hand
• Related to: machine-learning, deep-learning

Cons

• Specific tradeoffs depend on your use case

The Verdict

These tools serve different purposes. Pre-trained Models is a concept while Training From Scratch is a methodology. We picked Pre-trained Models based on overall popularity, but your choice depends on what you're building.

The Bottom Line

Pre-trained Models wins

Based on overall popularity. Pre-trained Models is more widely used, but Training From Scratch excels in its own space.