Model Training
Welcome back! Hope you enjoyed the previous post. If you haven’t gone over it yet, we highly recommend taking a peak because it introduces the concept of what a model is.
Training a model is like training a human brain, the more information it gathers the more it is able to find patterns that can result in generating a new system. The similarity is quite uncanny. Like a model, in order for a human to evolve, they tend to learn from experience which usually involves making mistakes and failing.
So how does a model get trained? does it go through rigorous training lessons?
If only that were the case, the process starts with “defining the problem statement” it refers to establishing what the ML (Machine Learning) model should achieve. This step also enables recognizing the appropriate inputs (commands, inquiries) and their respective outputs (produced answer); as a guide, it would be essential to answer questions such as“what is the main objective?”, “what is the input data?” and “what is the model trying to predict?”,
The next step continues with feeding the ML algorithm with existing data that includes samples of output data as well as the corresponding sets of input data that influenced the output results. The larger the dataset, the higher the probability of finding patterns between the inputs and output results. Regardless of the quantity, it is critical to justify correlations between inputs and outputs in order to measure levels of success.