Probabilistic models | Statistical models
In statistical classification, two main approaches are called the generative approach and the discriminative approach. These compute classifiers by different approaches, differing in the degree of statistical modelling. Terminology is inconsistent, but three major types can be distinguished, following : 1. * A generative model is a statistical model of the joint probability distribution on given observable variable X and target variable Y; 2. * A discriminative model is a model of the conditional probability of the target Y, given an observation x; and 3. * Classifiers computed without using a probability model are also referred to loosely as "discriminative". The distinction between these last two classes is not consistently made; refers to these three classes as generative learning, conditional learning, and discriminative learning, but only distinguish two classes, calling them generative classifiers (joint distribution) and discriminative classifiers (conditional distribution or no distribution), not distinguishing between the latter two classes. Analogously, a classifier based on a generative model is a generative classifier, while a classifier based on a discriminative model is a discriminative classifier, though this term also refers to classifiers that are not based on a model. Standard examples of each, all of which are linear classifiers, are: * generative classifiers: * naive Bayes classifier and * linear discriminant analysis * discriminative model: * logistic regression In application to classification, one wishes to go from an observation x to a label y (or probability distribution on labels). One can compute this directly, without using a probability distribution (distribution-free classifier); one can estimate the probability of a label given an observation, (discriminative model), and base classification on that; or one can estimate the joint distribution (generative model), from that compute the conditional probability , and then base classification on that. These are increasingly indirect, but increasingly probabilistic, allowing more domain knowledge and probability theory to be applied. In practice different approaches are used, depending on the particular problem, and hybrids can combine strengths of multiple approaches. (Wikipedia).
generative model vs discriminative model
understanding difference between generative model and discriminative model with simple example. all machine learning youtube videos from me, https://www.youtube.com/playlist?list=PLVNY1HnUlO26x597OgAN8TCgGTiE-38D6
From playlist Machine Learning
Set Distribution Networks: a Generative Model for Sets of Images (Paper Explained)
We've become very good at making generative models for images and classes of images, but not yet of sets of images, especially when the number of sets is unknown and can contain sets that have never been encountered during training. This paper builds a probabilistic framework and a practic
From playlist Papers Explained
(ML 13.5) Generative process specification
A compact way to specify a model is by its "generative process", using a convenient convention involving the graphical model.
From playlist Machine Learning
Generative Modeling by Estimating Gradients of the Data Distribution - Stefano Ermon
Seminar on Theoretical Machine Learning Topic: Generative Modeling by Estimating Gradients of the Data Distribution Speaker: Stefano Ermon Affiliation: Stanford University Date: May 12, 2020 For more video please visit http://video.ias.edu
From playlist Mathematics
Generative Model Basics - Unconventional Neural Networks p.1
Hello and welcome to a series where we will just be playing around with neural networks. The idea here is to poke around with various neural networks, doing unconventional things with them. Doing things like trying to teach a sequence to sequence model math, doing classification with a gen
From playlist Unconventional Neural Networks
Deep Generative Models, Stable Diffusion, and the Revolution in Visual Synthesis
We had the pleasure of having Professor Björn Ommer as a guest lecturer in my course SSY340, Deep machine learning at Chalmers University of Technology. Chapters: 0:00 Introduction 8:10 Overview of generative models 15:00 Diffusion models 19:37 Stable diffusion 26:10 Retrieval-Augmented
From playlist Invited talks
Generative AI and Long-Term Memory for LLMs (OpenAI, Cohere, OS, Pinecone)
Generative AI is what many expect to be the next big technology boom, and being what it is — AI — could have far-reaching implications far beyond what we'd expect. One of the most thought-provoking use cases of generative AI belongs to Generative Question-Answering (GQA). Now, the most
From playlist Recommended
Plug and Play Language Models: A Simple Approach to Controlled Text Generation | AISC
For slides and more information on the paper, visit https://aisc.ai.science/events/2020-01-13 Discussion lead: Raheleh Makki Discussion facilitator(s): Gordon Gibson, Royal Sequeira + Salman Mohammed Motivation: Large transformer-based language models (LMs) trained on huge text corpora
From playlist Natural Language Processing
CMU Neural Nets for NLP 2017 (8): Conditioned Generation
This lecture (by Graham Neubig) for CMU CS 11-747, Neural Networks for NLP (Fall 2017) covers: * Encoder-Decoder Models * Conditional Generation and Search * Ensembling * Evaluation * Types of Data to Condition On Slides: http://phontron.com/class/nn4nlp2017/assets/slides/nn4nlp-08-condl
From playlist CMU Neural Nets for NLP 2017
Lecture 19: Generative Models I
Lecture 19 is the first of two lectures about generative models. We compare supervised and unsupervised learning, and also compare discriminative vs generative models. We discuss autoregressive generative models that explicitly model densities, including PixelRNN and PixelCNN. We discuss a
From playlist Tango
DeepMind x UCL | Deep Learning Lectures | 9/12 | Generative Adversarial Networks
Generative adversarial networks (GANs), first proposed by Ian Goodfellow et al. in 2014, have emerged as one of the most promising approaches to generative modeling, particularly for image synthesis. In their most basic form, they consist of two "competing" networks: a generator which trie
From playlist Learning resources
Your Brain on Energy-Based Models: Applying and Scaling EBMs to Problems...- Will Grathwohl
Seminar on Theoretical Machine Learning Topic: Your Brain on Energy-Based Models: Applying and Scaling EBMs to Problems of Interest to Machine Learning Speaker: Will Grathwohl Affiliation: University of Toronto Date: March 10, 2020 For more video please visit http://video.ias.edu
From playlist Mathematics
Automated Text Generation & Data-Augmentation for Medicine, Finance, Law, and E-Commerce
This webinar teaches you how to leverage the human-level text generation capabilities of Large Transformer models to increase the accuracy of most NLP classifiers for Medicine, Finance, and Legal datasets with the Spark NLP library. We will also explore the next-generation capabilities f
From playlist AI & NLP Webinars
DeepMind x UCL | Deep Learning Lectures | 11/12 | Modern Latent Variable Models
This lecture, by DeepMind Research Scientist Andriy Mnih, explores latent variable models, a powerful and flexible framework for generative modelling. After introducing this framework along with the concept of inference, which is central to it, Andriy focuses on two types of modern latent
From playlist Learning resources
HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning (w/ Author)
#hypertransformer #metalearning #deeplearning This video contains a paper explanation and an interview with author Andrey Zhmoginov! Few-shot learning is an interesting sub-field in meta-learning, with wide applications, such as creating personalized models based on just a handful of data
From playlist Papers Explained
Deep Generative models and Inverse Problems - Alexandros Dimakis
Seminar on Theoretical Machine Learning Topic:Deep Generative models and Inverse Problems Speaker: Alexandros Dimakis Affiliation: University of Texas at Austin Date: April 23, 2020 For more video please visit http://video.ias.edu
From playlist Mathematics
Image generative modeling for future prediction or (...) - Couprie - Workshop 1 - CEB T1 2019
Couprie (Facebook) / 05.02.2019 Image generative modeling for future prediction or inspirational purposes Generative models, and in particular adversarial ones, are becoming prevalent in computer vision as they enable enhancing artistic creation, inspire designers, prove usefulness in s
From playlist 2019 - T1 - The Mathematics of Imaging
Leveraging Language Models for Training Data Generation and Tool Learning
see more slides, notes, and other material here: https://github.com/Aggregate-Intellect/practical-llms/ https://www.linkedin.com/in/gordon-gibson-874b3130/ ** Large Language Models and Synthetic Data Research on using unlabeled data to improve large language models is exciting, and the p
From playlist Practical Large Language Models