In a video generation system using Action Prediction (Figure 3), if you drop a drop a ball, the AI should predict the ball will fall on the floor because the implicit knowledges "gates" the model to generate a future where the ball goes upward like a Helium balloon. But how to build such "gating mechanism" (seen in Figure 4) that uses cognitive knowledge of cause & effect? Is it possible to design a futuristic AI that can be trusted by a doctor for a AI diagnosis inspite of sample from a out of distribution? Will mere selective prediction suffix or a deeper understanding of the semantic context and understanding of human anatomy activate a medical decision. During medical diagnosis, how can an AI avoid a false prediction based on conceptual knowledge of the medical domain?

Editor's note: You can read the previous post in this series, Power Laws in Deep Learning, here. In a previous post, we saw that the Fully Connected (FC) layers of the most common pre-trained Deep Learning display power law behavior. Remarkably, the FC matrices all lie within the Universality Class of Fat Tailed Random Matrices! We define a random matrix by defining a matrix of size, and drawing the matrix elements from a random distribution. In either case, Random Matrix Theory tells us what the asymptotic form of ESD should look like. But first, let's see what model works best.

Editor's note: This is one of a series of posts which act as a collection of a set of fantastic notes on the fast.ai The author of all of these notes, Hiromi Suenaga -- which, in sum, are a great supplement review material for the course or a standalone resource in their own right -- wanted to ensure that sufficient credit was given to course creators Jeremy Howard and Rachel Thomas in these summaries. Below you will find links to the posts in this particular series, along with an excerpt from each post. Find more of Hiromi's notes here. These notes will continue to be updated and improved as I continue to review the course to "really" understand it.

Reminder: RNN is not in any way different or unusual or magical -- just a standard fully connected network. There is no known good way. Somebody recently won a Kaggle competition by doing data augmentation which randomly inserted parts of different rows -- something like that may be useful here. But there has not been any recent state-of-the-art NLP papers that are doing this kind of data augmentation. When using an existing API which expects data to be certain format, you can either change your data to fit that format or you can write your own dataset sub-class to handle the format that your data is already in. Either is fine, but in this case, we will put our data in the format TorchText already support.

In the first session of our Deep Learning series, we described the basis of our approach to Deep Learning: the classical theory of neural networks. In this second we will try to focus on more practical aspects, such as the use of hyperparameters. One of the most fascinating ideas about Deep Learning is that each layer gets a data representation focused on the objective of the problem to be solved. So, the network as a whole generates an idea of each concept, derived from data. Some questions arise: "how are networks different from each other?" and "how can we build one that represents exactly what we want?"