Probability theory, Probability distribution, Discrete probability distribution, Probability density function, Random variable, Normal distribution

Controllable Neural Text Generation

On Jan 3, 2021
@Miles_Brundage shared
RT @lilianweng: The first post to start 2021💡: How to steer a powerful unconditioned language model to output what we want? It is still a challenging open research question. There are some ways although still only in limited domains. https://t.co/yDZnL6MCAE
Open

The modern langage model with SOTA results on many NLP tasks is trained on large scale free text on the Internet. It is challenging to steer such a model to generate content with desired attributes. ...

lilianweng.github.io
On Jan 3, 2021
@Miles_Brundage shared
RT @lilianweng: The first post to start 2021💡: How to steer a powerful unconditioned language model to output what we want? It is still a challenging open research question. There are some ways although still only in limited domains. https://t.co/yDZnL6MCAE
Open

Controllable Neural Text Generation

Controllable Neural Text Generation

The modern langage model with SOTA results on many NLP tasks is trained on large scale free text on the Internet. It is challenging to steer such a model to generate content with desired ...

omerbsezer/Generative_Models_Tutorial_with_Demo

omerbsezer/Generative_Models_Tutorial_with_Demo

Generative Models Tutorial with Demo: Bayesian Classifier Sampling, Variational Auto Encoder (VAE), Generative Adversial Networks (GANs), Popular GANs Architectures, Auto-Regressive Models, ...

Click here to read the article

Click here to read the article

Proceedings of Machine Learning Research 85:1–12, 2018 Machine Learning for Healthcare Deep Survival Analysis: Nonparametrics and Missingness Xenia Miscouridou ...

Tips for Training Likelihood Models

Tips for Training Likelihood Models

This is a tutorial on common practices in training generative models that optimize likelihood directly, such as autoregressive models and ...

Musings on typicality

Musings on typicality

A summary of my current thoughts on typicality, and its relevance to likelihood-based generative models.

Humans adapt their anticipatory eye movements to the volatility of visual motion properties

Humans adapt their anticipatory eye movements to the volatility of visual motion properties

Author summary Understanding how humans adapt to changing environments to make judgments or plan motor responses based on time-varying sensory information is crucial for psychology, ...

Probability Distributome: A Web Computational Infrastructure for Exploring the Properties, Interrelations, and Applications of Probability Distributions

Probability Distributome: A Web Computational Infrastructure for Exploring the Properties, Interrelations, and Applications of Probability Distributions

Probability distributions are useful for modeling, simulation, analysis, and inference on varieties of natural processes and physical phenomena. There are uncountably many probability ...

Intuitively Understanding Variational Autoencoders

Intuitively Understanding Variational Autoencoders

Why Variational Autoencoders are so useful in creating your own generative text, art and even music.

mlss2003_main.dvi

mlss2003_main.dvi

A partial list includes Anthony and Bartlett [2], Breiman, Friedman, Olshen, and Stone [3], Devroye, Gyo¨rfi, and Lugosi [4], Duda and Hart [5], Fukunaga [6], Kearns and Vazirani [7], ...

Stein Variational Gradient Descent

Stein Variational Gradient Descent

Topics: Measure Theory Kernels Reproducing Kernel Hilbert Space Machine Learning Basics Notes: In this class, we went over the basic mathematical concepts we will need throughout the rest ...

Statistics Review For Data Scientists And Management

Statistics Review For Data Scientists And Management

Need to review the statistics for data scientists? We review some basic algorithms, probability distributions and other concepts worth review.