Fine-tune Appoint Article For Free

in this video we'll discuss what fine-tuning is and how we can take advantage of it when building and training our own artificial neural networks fine tuning is very closely linked with the term transfer learning transfer learning occurs when we use knowledge that was gained from solving one problem and then apply it to a new but related problem for example knowledge gained from learning to recognize cars could potentially be applied in a problem of recognizing trucks fine tuning is a way of applying or utilizing transfer learning specifically fine tuning is a process that takes a model that's already been trained for a given task and then tuning or tweaking that model to make it perform a second similar task assuming the original task is similar to the new task using an artificial neural network that's already been designed and trained allows us to take advantage of what the model has already learned without having to develop it from scratch when building a model from scratch we have to try many approaches in a type of trial-and-error since we have to choose how many layers we're using what types of layers were using what order to put the layers and how many nodes to include in each layer we have to decide how much regularization to use what learning rate to use etc so with this it's easy to see that building and validating our own model can be a huge task in its own right depending on what data we're training it on that's what makes the fine-tuning approach so attractive if we can find the Train model that's already done one task well and that task is similar to ours in at least some remote way then we can take advantage of everything that model has already learned and apply it to our specific task now of course if the two tasks are different and there will be some information that the model has learned that may not apply to our new task or there may be new information that the model needs to learn from the data regarding the new task that wasn't learned from the previous task for example a model trained on cars is not going to have ever seen a truck bed so this features something new the model would have to learn about if we're going to be training it to recognize trucks but think about everything else that our new model for recognizing trucks could use from the original model that was trained only on cars this already trained model has learned to understand edges and shapes and textures and more objectively headlights door handles windshields tires etc all of these learned features are definitely things we could benefit from in our new model for classifying trucks so this sounds fantastic right but how do we actually technically implement this so going back to the example we just mentioned if we have a model that's already been trained to recognize cars and we want to fine-tune this model to recognize trucks we can first import our original model that was used on the cars problem then for simplicity purposes let's say we removed just...