- Terminology (A to D)
- Bayes Theorem
- Big Data
- Chatbot: A Beginner’s Guide
- Computational Thinking
- Computer Vision
- Confusion Matrix
- Convolutional Neural Networks
- Data Fabric
- Data Storytelling
- Data Science
- Data Scientist
- Decision Tree
- Deep Learning
- Deep Reinforcement Learning
- Digital Twin
- Dimensionality Reduction
- Terminology (E to K)
- Terminology (L to Q)
- Terminology (R to Z)
What are RNNs and LSTMs in Deep Learning?
Table Of Contents
Many of the most impressive advances in natural language processing and AI chatbots are driven by Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks. RNNs and LSTMs are special neural network architectures that are able to process sequential data, data where chronological ordering matters. LSTMs are essentially improved versions of RNNs, capable of interpreting longer sequences of data. Let’s take a look at how RNNs and LSTMS are structured and how they enable the creation of sophisticated natural language processing systems.
What are Feed-Forward Neural Networks?
So before we talk about how Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) work, we should discuss the format of a neural network in general.
A neural network is intended to examine data and learn relevant patterns, so that these patterns can be applied to other data and new data can be classified. Neural networks are divided into three sections: an input layer, a hidden layer (or multiple hidden layers), and an output layer.
The input layer is what takes in the data into the neural network, while the hidden layers are what learn the patterns in the data. The hidden layers in the dataset are connected to the input and output layers by “weights” and “biases” which are just assumptions of how the data points are related to each other. These weights are adjusted during training. As the network trains, the model’s guesses about the training data (the output values) are compared against the actual training labels. During the course of training, the network should (hopefully) get more accurate at predicting relationships between data points, so it can accurately classify new data points. Deep neural networks are networks that have more layers in the middle/more hidden layers. The more hidden layers and more neurons/nodes the model has, the better the model can recognize patterns in the data.
Regular, feed-forward neural networks, like the ones I’ve described above are often called “dense neural networks”. These dense neural networks are combined with different network architectures that specialize in interpreting different kinds of data.
What are RNNs (Recurrent Neural Networks)?
Recurrent Neural Networks take the general principle of feed-forward neural networks and enable them to handle sequential data by giving the model an internal memory. The “Recurrent” portion of the RNN name comes from the fact that the input and outputs loop. Once the output of the network is produced, the output is copied and returned to the network as input. When making a decision, not only the current input and output are analyzed, but the previous input is also considered. To put that another way, if the initial input for the network is X and the output is H, both H and X1 (the next input in the data sequence) are fed into the network for the next round of learning. In this way, the context of the data (the previous inputs) is preserved as the network trains.
The result of this architecture is that RNNs are capable fo handling sequential data. However, RNNs suffer from a couple of issues. RNNs suffer from the vanishing gradient and exploding gradient problems.
The length of sequences that an RNN can interpret are rather limited, especially in comparison to LSTMs.
What are LSTMs (Long Short-Term Memory Networks)?
Long Short-Term Memory networks can be considered extensions of RNNs, once more applying the concept of preserving the context of inputs. However, LSTMs have been modified in several important ways that allow them to interpret past data with superior methods. The alterations made to LSTMs deal with the vanishing gradient problem and enable LSTMs to consider much longer input sequences.
LSTM models are made up of three different components, or gates. There’s an input gate, an output gate, and a forget gate. Much like RNNs, LSTMs take inputs from the previous timestep into account when modifying the model’s memory and input weights. The input gate makes decisions about which values are important and should be let through the model. A sigmoid function is used in the input gate, which makes determinations about which values to pass on through the recurrent network. Zero drops the value, while 1 preserves it. A TanH function is used here as well, which decides how important to the model the input values are, ranging from -1 to 1.
After the current inputs and memory state are accounted for, the output gate decides which values to push to the next time step. In the output gate, the values are analyzed and assigned an importance ranging from -1 to 1. This regulates the data before it is carried on to the next time-step calculation. Finally, the job of the forget gate is to drop information that the model deems unnecessary to make a decision about the nature of the input values. The forget gate uses a sigmoid function on the values, outputting numbers between 0 (forget this) and 1 (keep this).
An LSTM neural network is made out of both special LSTM layers that can interpret sequential word data and the densely connected like those described above. Once the data moves through the LSTM layers, it proceeds into the densely connected layers.
Blogger and programmer with specialties in Machine Learning and Deep Learning topics. Daniel hopes to help others use the power of AI for social good.