Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:00,420 --> 00:00:05,990 Hello and welcome to the intuition tutorials for the artificial neural networks part of the course. 2 00:00:06,060 --> 00:00:08,760 Super excited to get these things started. 3 00:00:09,000 --> 00:00:11,870 And today we're going to find out how we're going to tackle this section. 4 00:00:11,880 --> 00:00:14,760 So in this section we will learn the following things. 5 00:00:14,760 --> 00:00:20,550 First of all we'll talk about the neuron so there'll be a little bit of neuroscience and we'll find 6 00:00:20,550 --> 00:00:25,700 out a bit about how the human brain works and why we are trying to replicate that. 7 00:00:25,710 --> 00:00:32,160 And we'll also see what the main building block of a neural network of the neuron looks like. 8 00:00:32,160 --> 00:00:37,740 Then in the next tutorial We'll talk about the activation function and we'll look at a couple of examples 9 00:00:37,740 --> 00:00:43,980 of attrition functions that you could use in your neural networks and we'll find out which ones of which 10 00:00:43,980 --> 00:00:52,770 one of them is the most commonly used one in neural networks and in which layers you'd rather use which 11 00:00:52,770 --> 00:00:53,770 functions. 12 00:00:53,860 --> 00:00:56,430 There was talk about how neural networks work. 13 00:00:56,430 --> 00:01:03,990 So in contrast to what you would expect and what it was probably conveyed in other courses and tutorials 14 00:01:04,260 --> 00:01:10,800 we're not going to go into the learning we're actually going to go into the working of the neural networks 15 00:01:10,800 --> 00:01:18,690 first because that way by seeing a neural network in action that will allow us to understand what we're 16 00:01:19,020 --> 00:01:20,740 aiming towards what our goal is. 17 00:01:20,740 --> 00:01:27,120 So here we'll look at an example of a neural network we're going to look at a very simplified and very 18 00:01:27,120 --> 00:01:33,060 simplified hypothetical example or when your own network working to predict housing prices are basically 19 00:01:33,060 --> 00:01:34,830 real estate prices. 20 00:01:34,980 --> 00:01:40,350 And by looking at that example we'll understand better exactly what we're aiming towards and what we 21 00:01:40,350 --> 00:01:41,620 want to achieve in the end. 22 00:01:42,060 --> 00:01:49,560 And then we will move on to understanding how neural networks learn because that way we'll be more prepared 23 00:01:49,560 --> 00:01:51,070 for what's coming. 24 00:01:51,180 --> 00:01:53,010 Then we'll talk about gradient descent. 25 00:01:53,010 --> 00:02:00,750 This is also part of neural networks learning and we'll understand how that algorithm is better than 26 00:02:00,750 --> 00:02:08,670 just the brute force method that you might be intending or willing to take as a first resort or first 27 00:02:08,940 --> 00:02:10,140 method that comes to mind. 28 00:02:10,140 --> 00:02:14,400 So we'll find out how great the advantage of gradient descent are. 29 00:02:14,520 --> 00:02:17,130 And then we'll talk about stochastic gradient descent. 30 00:02:17,140 --> 00:02:23,580 It's a it's a continuation of the great and decent tutorial but it's an even better and even stronger 31 00:02:23,580 --> 00:02:26,120 method and we'll find out exactly how it works. 32 00:02:26,220 --> 00:02:33,060 And finally we'll wrap things up by mentioning the important things about back propagation and summarizing 33 00:02:33,060 --> 00:02:40,400 everything in a step by step set of instructions for running your artificial neural networks. 34 00:02:40,440 --> 00:02:46,230 I hope this all sounds very exciting to you because I am very excited myself and I can't wait to get 35 00:02:46,230 --> 00:02:46,810 started. 36 00:02:46,950 --> 00:02:49,310 I look forward to seeing you on the first tutorial. 37 00:02:49,320 --> 00:02:51,420 And until then enjoy deep learning. 4241