- Bob Anderson
- Sign In
- IntuitiveML
Loss Functions: What are they and why are they important?
Jul 4, 2020Loss functions tell us how wrong our predictions are during training. We then use that information to optimize our machine learning model.
Loss functions tell us how wrong our predictions are during training. We then use that information to optimize our machine learning model.
- IntuitiveML
What is a confusion matrix? How does it work? Why do we care?
Jun 26, 2020A confusion matrix is a nice way of visualizing the performance of your models.
A confusion matrix is a nice way of visualizing the performance of your models.
- IntuitiveML
Intuition: What is Accuracy, Precision, and Recall in machine learning, and how do they work?
Jun 18, 2020You have a model, and now you want to judge how well it performs. How do you measure model effectiveness?
You have a model, and now you want to judge how well it performs. How do you measure model effectiveness?
- IntuitiveML
Intuition: How does the Heaviside Activation Function work?
Jun 11, 2020Early on in the development of neural networks, most activation functions were created to represent the action potential firing in a neuron, because after all, neural networks were originally inspired by how the brain works.
Early on in the development of neural networks, most activation functions were created to represent the action potential firing in a neuron, because after all, neural networks were originally inspired by how the brain works.
- IntuitiveML
Terms: Nonlinearity
Jun 4, 2020While nonlinear does mean not linear, there are a couple of small catches that aren’t obvious right away.
While nonlinear does mean not linear, there are a couple of small catches that aren’t obvious right away.
- IntuitiveML
Terms: Activation functions
Jun 3, 2020The original idea behind the activation function is to only propagate signals that are important and ignore signals that aren’t – similar to how neurons in our brain propagate signals.
The original idea behind the activation function is to only propagate signals that are important and ignore signals that aren’t – similar to how neurons in our brain propagate signals.
- IntuitiveML
Neural Network Caveats (Intuition: Artificial Neural Networks Follow-up)
Jun 2, 2020However, this doesn’t guarantee that the network is modeling the actual function. It guarantees that it is possible to model that function, but in reality, your neural network is modeling the function over your data set.
However, this doesn’t guarantee that the network is modeling the actual function. It guarantees that it is possible to model that function, but in reality, your neural network is modeling the function over your data set.
- IntuitiveML
What is the difference between a Deep Neural Network and an Artificial Neural Network?
Jun 1, 2020Technically, an artificial neural network (ANN) that has a lot of layers is a Deep Neural Network (DNN). In practice though, a deep neural network is just a normal neural network where the layers of the network are abstracted out, or a network that uses functions not typically found in an artificial neural network.
Technically, an artificial neural network (ANN) that has a lot of layers is a Deep Neural Network (DNN). In practice though, a deep neural network is just a normal neural network where the layers of the network are abstracted out, or a network that uses functions not typically found in an artificial neural network.
- IntuitiveML
Intuition: Artificial Neural Networks
May 30, 2020Every layer in our network just adds another layer of nesting to the function we are building. So when we create an artificial neural network (ANN), all we are doing is creating a complicated function on the inputs. So how does creating this function help solve our problem?
Every layer in our network just adds another layer of nesting to the function we are building. So when we create an artificial neural network (ANN), all we are doing is creating a complicated function on the inputs. So how does creating this function help solve our problem?
- IntuitiveML
Intuition: Perceptrons and Artificial Neural Networks
May 29, 2020Perceptrons are just neural networks with a single output node, so how a perceptron works and how a neuron in a neural network works are the exact same.
Perceptrons are just neural networks with a single output node, so how a perceptron works and how a neuron in a neural network works are the exact same.
- IntuitiveML
Types of Machine Learning: Supervised, Unsupervised, Semi-supervised, Self-supervised, and Reinforcement Learning
May 28, 2020Supervised, Unsupervised, Semi-supervised, Self-supervised, and Reinforcement Learning are all different ways of learning from data to tackle problems.
Supervised, Unsupervised, Semi-supervised, Self-supervised, and Reinforcement Learning are all different ways of learning from data to tackle problems.
- IntuitiveML
Terms: Train vs Evaluate vs Prediction
May 27, 2020When you start learning and creating machine learning models, you might run into a few different a few different ways used to describe how your model is running or being used.
When you start learning and creating machine learning models, you might run into a few different a few different ways used to describe how your model is running or being used.
- IntuitiveML
What is Artificial Intelligence? What is Machine Learning?
May 26, 2020Artificial intelligence is intelligence that is demonstrated by machines, not people. In reality, the term is usually used to describe how computers mimic the different parts of human intelligence such as planning, learning, reasoning, and so on.
Artificial intelligence is intelligence that is demonstrated by machines, not people. In reality, the term is usually used to describe how computers mimic the different parts of human intelligence such as planning, learning, reasoning, and so on.
subscribe via RSS