Training Optimization So by now we’ve learned how to build a deep neural network and how to train it to fit our data. Sometimes however, we go out there and train on ourselves and find out that nothing works as planned. Why? Because there are many things that can fail. Read more…
Gradient Descent with Squared Errors We want to find the weights for our neural networks. Let’s start by thinking about the goal. The network needs to make predictions as close as possible to the real values. To measure this, we use a metric of how wrong the predictions are, the error. Read more…
Introduction So let’s start with two questions, what is deep learning, and what is it used for? The answer to the second question is pretty much everywhere. Recent applications include things such as beating humans in games such as Go, or even jeopardy, detecting spam in emails, forecasting stock prices, Read more…
What is a neural network? The term, Deep Learning, refers to training Neural Networks, sometimes very large Neural Networks. So what exactly is a Neural Network? In this video, let’s try to give you some of the basic intuitions. Let’s start to the Housing Price Prediction example. Let’s say you have a data sets Read more…
Introduction A hyper parameter is a variable that we need to set before applying a learning algorithm into a dataset. The challenge with hyper parameters is that there are no magic numbers that work everywhere. The best numbers depend on each task and each dataset. Generally speaking, we can break Read more…
Learn how to represent memory in code. Then define and train RNNs in Pytorch and apply them to tasks that involve sequential data The practical notebook can be found at http://14.232.166.121:8880/lab/workspaces/andy > char_rnn > Character_Level_RNN_Exercise.ipynb
RNN vs LSTM let’s say we have a regular neural network which recognizes images and we fitted this image. And the neural neural network guesses that the image is most likely a dog with a small chance of being a wolf and an even smaller chance of being a goldfish. But, Read more…
LSTMs for Question Answering LSTMs come in either or mode. In both modes, an LTSM processes a batch of stateless stateful labeled training vectors. An LSTM works itself one step ( ) at a time through an input feature vector, updating its cell state at each step. In stateless mode, Read more…
In this blog series we will discuss about Question Answering: answering a question on the basis of a number of facts. This task involves using memory: facts are stored in memory, and the question refers back to past information. How do the various models for sequential processing stack up to Read more…
Training data is an essential part of every machine learning model. It is no different when it comes to conversational AI. We designed Rasa Core so that instead of writing rules, your assistant could observe what real conversations look like, learn from them and use that knowledge to manage the dialogue. Modelling Read more…