What will you learn? Ask any machine learning expert! They will all have to google the answer to this question: “What was the derivative of the Softmax function w.r.t (with respect to) its input again?” The reason behind this forgetfulness is that Softmax(z) is a tricky function, and people tend to forget the process of …
The Gradient Descent Rule https://www.youtube.com/watch?v=gYqG4OT2Kj4 When training a model, we strive to minimize a certain error function (). This error function gives us an indication as to how well is our model doing on our training data. So, in general, the lower it is, the better our model is doing on the training set. Make …
What is Reproducibility All About? As a computer scientist, or as an academician, you do experiments with a bunch of algorithms. Let’s say you have coded a machine learning algorithm, like an Artificial Neural Network, and after doing your experiments with different datasets, you have found out that the best type of neural network has …
What We Have Learned So Far … So far, we have learned that the Delta rule guarantees to converge to a model that fits our data the best! It just so happens that the best fit might be a terrible model but still it is the best that the Delta rule has been able to …
The Beauty that is the Delta Rule In general, there are 2 main ways to train an Artificial Neural Network (ANN). In our previous post , I have told you about the popular perceptron rule that has been around for a long time. We also said that the perceptron training rule is guaranteed to converge …
The Perceptron Training Rule It is important to learn the training process of huge neural networks. However, we need to simplify this by first understanding how a simple perceptron is trained, and how its weights are updated! Only then, will we be able to understand the dynamics of complicated and monstrous neural networks, such as …
ECML-PKDD-2019 on EBFDD networks for Anomaly Detection This paper introduces the Elliptical Basis Function Data Descriptor (EBFDD) network, a one-class classification approach to anomaly detection based on Radial Basis Function (RBF) neural networks. The EBFDD network uses elliptical basis functions, which allows it to learn sophisticated decision boundaries while retaining the advantages of a shallow …
ECML-PKDD-2019: Elliptical Basis Function Data Descriptor (EBFDD) for Anomaly Detection Read More »
What will you Learn in this Post? Neural Networks are function approximators. For example, in a supervised learning setting, given loads of inputs and loads of outputs in our training data, a neural network is capable of finding the hidden mapping between the those inputs and outputs. It can also, hopefully, generalize its acquired knowledge …
Train a Perceptron to Learn the AND Gate from Scratch in Python Read More »
Hello friends and welcome to MLDawn! So what sometimes concerns me is the fact that magnificent packages such as PyTorch (indeed amazing), TensorFlow (indeed a nightmare), and Keras (indeed great), have prevented machine learning enthusiasts to really learn the science behind how the machine learns. To be more accurate, there is nothing wrong with having …
This talk was delivered in PyData meetup. This was an amazing meetup with great talks and ideas being discussed! Thanks to organizers, I was also invited to give a talk. Below is the summary: In this talk we learn about what Artificial Neural Networks (ANNs) are, and find out how in general, Maximum Likelihood …
Birth of Error Functions in Artificial Neural Networks Read More »