Mohit Deshpande 
Neural Networks are very powerful models for classification tasks. But what about regression? Suppose we had a set of data points and wanted to project that trend into the future to make predictions. Regression has many applications in finance, physics, biology, and many other fields. Radial Basis Function Networks (RBF nets) are used for exactly … Read more
Face recognition is ubiquitous in science fiction: the protagonist looks at a camera, and the camera scans his or her face to recognize the person. More formally, we can formulate face recognition as a classification task, where the inputs are images and the outputs are people’s names. We’re going to discuss a popular technique for face … Read more
Clustering is an essential part of any data analysis. Using an algorithm such as K-Means leads to hard assignments, meaning that each point is definitively assigned a cluster center. This leads to some interesting problems: what if the true clusters actually overlap? What about data that is more spread out; how do we assign clusters then? … Read more
Neural Networks have become incredibly popular over the past few years, and new architectures, neuron types, activation functions, and training techniques pop up all the time in research. But without a fundamental understanding of neural networks, it can be quite difficult to keep up with the flurry of new work in this area. To understand … Read more
The challenge of text classification is to attach labels to bodies of text, e.g., tax document, medical form, etc. based on the text itself. For example, think of your spam folder in your email. How does your email provider know that a particular message is spam or “ham” (not spam)? We’ll take a look at … Read more
One of the most widely-used and robust classifiers is the support vector machine. Not only can it efficiently classify linear decision boundaries, but it can also classify non-linear boundaries and solve linearly inseparable problems. We’ll be discussing the inner workings of this classification jack-of-all-trades. We first have to review the perceptron so we can talk … Read more
Think back to the time you first learned a skill: driving a car, playing an instrument, cooking a recipe. Let’s consider the example of playing chess. Initially, it might have seemed difficult, but, as you played more and more, it became easier to understand the game. After playing many games of chess, you are much … Read more
One challenge of neural or deep architectures is that it is difficult to determine what exactly is going on in the machine learning algorithm that makes a classifier decide how to classify inputs. This is a huge problem in deep learning: we can get fantastic classification accuracies, but we don’t really know what criteria a … Read more
Recurrent Neural Networks (RNNs) are used in all of the state-of-the-art language modeling tasks such as machine translation, document detection, sentiment analysis, and information extraction. Previously, we’ve only discussed the plain, vanilla recurrent neural network. We’ll be discussing state-of-the-art models that are used by companies like Google, Amazon, and Microsoft for language tasks. We’ll first … Read more
Convolutional Neural Networks (CNNs) are used in all of the state-of-the-art vision tasks such as image classification, object detection and localization, and segmentation. Previously, we’ve only discussed the LeNet-5 architecture, but that hasn’t been used in practice for decades! We’ll discuss some more modern and complicated architectures such as GoogLeNet, ResNet, and DenseNet. These are … Read more
