Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

inFERENCe

www.inference.vc/rss/
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 15

  1. The Future of Software

    (inFERENCe)

    The world of software is undergoing a shift not seen since the advent of compilers in the 1970s.

  2. Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On

    (inFERENCe)

    Ten years ago this week, I wrote a provocative and bold post that blew up, made it to top spot on HackerNews.

  3. Discrete Diffusion: Continuous-Time Markov Chains

    (inFERENCe)

    This post, intended to be the first in a series related to discrete diffusion models, has been sitting in my drafts for months.

  4. We may finally crack Maths. But should we?

    (inFERENCe)

    Automating mathematical theorem proving has been a long standing goal of artificial intelligence and indeed computer science.

  5. Mortal Komputation: On Hinton's argument for superhuman AI.

    (inFERENCe)

    Last week in Cambridge was Hinton bonanza.

  6. Autoregressive Models, OOD Prompts and the Interpolation Regime

    (inFERENCe)

    A few years ago I was very much into maximum likelihood-based generative modeling and autoregressive models (see this, this or this).

  7. We May be Surprised Again: Why I take LLMs seriously.

    (inFERENCe)

    "Deep Learning is Easy, Learn something Harder" - I proclaimed in one of my early and provocative blog posts from 2016.

  8. Implicit Bayesian Inference in Large Language Models

    (inFERENCe)

    This intriguing paper kept me thinking long enough for me to I decide it's time to resurrect my blogging (I started writing this during ICLR review period, and realised it might be a good idea to wait until that's concluded) Sang Michael Xie, Aditi Raghun…

  9. Eastern European Guide to Writing Reference Letters

    (inFERENCe)

    Excruciating.

  10. Causal inference 4: Causal Diagrams, Markov Factorization, Structural Equation Models

    (inFERENCe)

    This post is written with my PhD student and now guest author Patrik Reizinger and is part 4 of a series of posts on causal inference: Part 1: Intro to causal inference and do-calculus Part 2: Illustrating Interventions with a Toy Example Part 3: Counterf…

  11. On Information Theoretic Bounds for SGD

    (inFERENCe)

    Few days ago we had a talk by Gergely Neu, who presented his recent work: Gergely Neu Information-Theoretic Generalization Bounds for Stochastic Gradient Descent I'm writing this post mostly to annoy him, by presenting this work using super hand-wavy intu…

  12. Notes on the Origin of Implicit Regularization in SGD

    (inFERENCe)

    I wanted to highlight an intriguing paper I presented at a journal club recently: Samuel L Smith, Benoit Dherin, David Barrett, Soham De (2021) On the Origin of Implicit Regularization in Stochastic Gradient Descent There's actually a related paper that c…

  13. An information maximization view on the $\beta$-VAE objective

    (inFERENCe)

    guest post with Dóra Jámbor This is a half-guest-post written jointly with Dóra, a fellow participant in a reading group where we recently discussed the original paper on $\beta$-VAEs: Irina Higgins et al (ICLR 2017): $\beta$-VAE: Learning Basic Visual Co…

  14. Some Intuition on the Neural Tangent Kernel

    (inFERENCe)

    Neural tangent kernels are a useful tool for understanding neural network training and implicit regularization in gradient descent.

  15. Notes on Causally Correct Partial Models

    (inFERENCe)

    I recently encountered this cool paper in a reading group presentation: Rezende et al (2020) Rezende Causally Correct Partial Models for Reinforcement Learning It's frankly taken me a long time to understand what was going on, and it took me weeks to write