"Exploration of Neural Networks: This incredible structure that's in our mind and there's only echoes of it. Small shadows of it in our artificial neural networks that we're able to create, but nevertheless those echoes are inspiring to us."

"Exploring TensorFlow Capabilities: There's different levels of APIs. Much of what we'll do in this course will be the highest level API with Keras. But there's also the ability to run in the browser with TensorFlow JS, on the phone with TensorFlow Lite, in the cloud without any need to have computer hardware or anything, any of the library set up on your own machine. You can run all the code that we're providing in the cloud with Google Colab Collaboratory."

"Challenges in Visual Perception for Autonomous Driving: But what they're thinking about we're not even we haven't even begun to really think about that problem and we do it trivially as human beings. And I think at the core of that I think I'm harboring on the visual perception problem because it's one we take really for granted as human beings especially when trying to solve real world problems, especially when trying to solve autonomous driving, is we've have 540,000,000 years of data for visual perception so we take it for granted. We don't realize how difficult it is. The visual perception is nevertheless extremely difficult at all the at every single layer of what's required to perceive, interpret and understand the fundamentals of a scene."

"Deep Learning and its Limitations: And there's this rising sea as we solve problem after problem. The question can the methodology in and the approach of deep learning of everything we're doing now keep the sea rising? Or do fundamental breakthroughs have to happen in order to generalize and solve these problems? If you have good enough data there's good enough ground truth and can be formalized we can solve it."

"AI Breakthroughs: The thing that enabled a lot of breakthrough performances in the past few years is batch normalization. It's performing this kind of same normalization later on in the network. And batch renorm solves a lot of these problems doing inference."

"Unlocking the Potential of Deep Learning: So convolutional neural networks, the thing that enables image classification. So these convolutional filters slide over the image and are able to take advantage of the spatial and variance of visual information that a cat in the top left corner is the same as features associated with cats in the top right corner and so on."

"Understanding Semantic Segmentation: Every single in full scene classification, full scene segmentation class what every single pixel which class that pixel belongs to. And the fundamental aspect there is we'll cover a little bit or a lot more on Wednesday is taking a image classification network, chopping it off at some point and then having which is performing the encoding step of compressing a representation of the scene and taking that representation with a decoder, upsampling in a dense way the So taking that representation and upsampling the pixel level classification."

"Understanding Neural Networks: 'The main thing is the middle, the hidden layer. That representation gives you the embedding that represents these words in such a way where in the Euclidean space the ones that are close together are semantically together and the ones that are not are semantically far apart. And natural language and other sequence data, text speech audio video relies on recurrent neural networks.'"

"Evolution of AI and Deep Learning: It's super exciting that as opposed to like I said stacking Lego pieces yourself, the final result is essentially you step back and you say here's I have a data set with the with the labels with the ground truth which is what Google the dream of Google AutoML is. I have the data set, you tell me what kind of neural network will do best on this data set. And that's it."

"AI Evolution and Humanity's Role: It's taking further and further steps and there's been a lot of exciting ideas going by different names. Basically removing a human as much as possible from the menial task and involving a human only on the fundamental side. And the things that us humans at least pretend to be quite good at which is understanding the fundamental big questions, understanding the data that empowers us to solve real world problems and understand the ethical balance that needs to be struck in order to solve those problems well."