{"id":11608,"date":"2018-08-01T11:11:46","date_gmt":"2018-08-01T11:11:46","guid":{"rendered":"http:\/\/stblog.lunaeme.com\/?p=11608"},"modified":"2023-09-20T15:39:24","modified_gmt":"2023-09-20T15:39:24","slug":"wild-data-part-one-augmentation-2","status":"publish","type":"post","link":"https:\/\/www.stratio.com\/blog\/wild-data-part-one-augmentation-2\/","title":{"rendered":"Wild Data Part 1: Augmentation"},"content":{"rendered":"

Let\u2019s imagine that you want to buy a new car, and you fall in love with this new car\u2019s brand. Because you really want that car, the car\u2019s brand comes out everywhere in your daily life, even though the amount of these cars remain the same. Our brain is trained to focus on what it wants to see.<\/p>\n

<\/p>\n

As we have already seen in the previous posts, Deep Learning was inspired by biological systems (neurons<\/a> and memory<\/a>). Using what we learnt from Cognitive Sciences we\u2019ve replicated it somehow in an artificial world. We already highlighted that Neuroscience and Deep Learning are very different disciplines, but it is very interesting to state what similarities we find in the cognitive (biological) system with what we have learnt from the functioning of deep (artificial) Neural Networks. Addressing this knowledge would greatly help us to better understand both concepts and their motivation.<\/p>\n

\"Training<\/p>\n

Ok, let\u2019s now imagine that you have a dataset that contains different cars, and like the majority of real-world dataset, are unbalanced. Therefore, you need to improve our training data<\/a>. Our dataset could contain more examples of our favorite brand, this will have an impact on the way the model predicts at the time of inference. Likewise, even if we have our dataset balanced and most of our favorite cars are the same color, the similar thing will happen. In this way, we will also get confused when we see another car of the same color because we will think that this might be our favorite car. Convolutional neural networks might have a related problem. This happens because that\u2019s how machine learning algorithms work. There are many factors here, but Deep Learning will merely learn the bias<\/a>.<\/p>\n

Invariance<\/h2>\n

Invariance is the ability of convolutional neural networks to classify objects even when placed in different orientations. The best way to achieve this will be with data and just more data! Sometimes we are simply unable to collect more data… but we do have several mechanisms to increase a training dataset.<\/p>\n

Let’s first empathize with this concept from the human perspective – a biological neural network. Take a look at the next picture:<\/p>\n

\"Dog\"
What do you see in this image?<\/figcaption><\/figure>\n

What do you see in this picture? Why is it so hard for us to identify what\u2019s in this image? This has all to do with the way we\u2019re built. Our brain has evolved to try to find logical solutions and, as we are all used to see two eyes and a mouth when we see a face, we will try to find something that will probably lead us to discover a completely normal dog with a tilted head.<\/p>\n

In the same way, we learnt that convolutional neural networks are invariant to:<\/p>\n