https://speakerdeck.com/andreapi 2017-12-14 11:44:28 -0500 Deep Learning can be understood as a set of tools to efficiently train neural networks with many layers, without overfitting the model to the training set. While a theoretical explanation for the generalization power of large capacity deep neural network is still lacking, the availability of very user-friendly libraries (e.g., Keras,PyTorch, etc.) allows even people without a formal training in Deep Learning to experiment and build performing networks. This presentation will show an application to a simple image classification benchmark. Deep Learning can be understood as a set of tools to efficiently train neural networks with many layers, without overfitting the model to the training set. While a theoretical explanation for the generalization power of large capacity deep neural network is still lacking, the availability of very user-friendly libraries (e.g., Keras,PyTorch, etc.) allows even people without a formal training in Deep Learning to experiment and build performing networks. This presentation will show an application to a simple image classification benchmark. Thu, 14 Dec 2017 00:00:00 -0500 https://speakerdeck.com/andreapi/deep-learning-the-easy-way https://speakerdeck.com/andreapi/deep-learning-the-easy-way