Dhagash Mehta, Ph.D.

For his debut TDS article, Jeremi Nuer presents a thoughtful walkthrough of a recent paper on model interpretability: "We want to have finer-tuned control over LLMs. Being able to detect when certain features are active, and tune how active they are in the middle of generating output, is an amazing tool to have in our toolbox."

18

🚀 While many studies highlight LLMs' success in answering medical questions, research from Yanjun Gao, PhD, and colleagues takes it a step further. They evaluated LLMs on real-world EHR datasets for clinical prediction, comparing them directly against classical machine learning models—widely regarded as state-of-the-art in this field. By examining tasks like mortality prediction and hospital length-of-stay prediction, which greatly influence clinical workflows, the findings demonstrate that LLMs have significant potential to advance clinical predictive modeling.

7

One of our recent AI projects involves wrangling arbitrary, unstructured data into clean, defined categories. The core challenge? LLMs hallucinating categories (among other things!). On the latest from the Dev Blog, Dan Girellini shares an approach using dynamic Pydantic models to enforce flexible, structured output from LLMs. This technique offers a robust way to control AI outputs while accommodating varying scenarios.

7

Advances in Bayesian Deep Neural Network Ensembles and Active Learning for Preference Modeling Quick read: https://lnkd.in/gzZB2VGh Paper 1: https://lnkd.in/gBkwknBZ Paper 2: https://lnkd.in/gNrqnqg9

18

🧠 Physics meets finance! Yuchen Dong of MathWorks discusses using Physics-Informed Neural Networks for faster, accurate option pricing. Ideal for quant experts! 📽️ Watch now & download slides: https://lnkd.in/eSkRfWJ2 https://lnkd.in/e8X67Qvc 🔗 #MathWorksFinConf2024 #NeuralNetworks #OptionPricing

25

Computer science professor at University of California, Berkeley : Stop pursuing CS = You are welcome to study CS for Complexity slaying of Computational challenges but not for jobs. Here is what Prof. James O'Brien said: I've been a professor of computer science at UC Berkeley since 2000. Recently, I've noticed how difficult it is for tech graduates to enter the job market right now. At least in technology, it's a very different landscape than it has been in the past. It's not just my students; it's a hard time for everyone right now. Over the years, students I've worked with, taught, or known from other schools have typically had little trouble finding a job after graduating with a tech degree. There were lots of opportunities. Quite often, recent graduates would receive multiple offers and be left to try to decide between two really great choices. But now, things have changed. There's still demand for people, and some people are getting jobs, but not across the entire industry. Our view from Berkeley is also a little distorted because we're one of the top schools, so most of our students are still getting offers. But rather than getting five great offers, they might only get one great offer or an offer from their second choice. This is certainly not what we've seen in the past. There are also people coming from other schools that don't have quite the strong reputation that Berkeley does, and they're not getting job offers at all. Some programming roles are disappearing. It's not just the technology jobs that are being affected. Any "hands-on keyboard job" is at risk of being contracted out offshore or outsourced to AI. Another problem is that many companies are also trying to consolidate a bit. These things are all coming together like a perfect storm. In tech, programming positions that aren't that demanding are disappearing. They are still entry-level jobs that involve basically babysitting the AI — but these systems are getting better very quickly. = This matches No Work Theory. What? No one should ever work. WTF?? Work is the source of nearly all the misery in the world. Almost any evil you’d care to name comes from working or from living in a world designed for work. In order to stop suffering, we have to stop working. That doesn’t mean we have to stop doing things. It does mean creating a new way of life based on play; in other words, a ludic revolution. By “play” I mean also festivity, creativity, conviviality, commensality, and maybe even art. There is more to play than child’s play, as worthy as that is. I call for a collective adventure in generalized joy and freely interdependent exuberance. Play isn’t passive. Doubtless we all need a lot more time for sheer sloth and slack than we ever enjoy now, regardless of income or occupation, but once recovered from employment-induced exhaustion nearly all of us want to act. Pursue 007 life based on Universal Basic Income instead of 996 corporate slavery. That is Utopia.

45

37 Comments

I tried to explain LLM hallucination intuitively using the concept of semantic entropy. I treated the two different scenarios of short response and long response separately. Hallucination mechanism with long response is more complex since the output typically weaves through multiple concepts. #ai #llm #hallucination #semantic #entropy https://lnkd.in/gF2_2H6w

35

5 Comments

Why do LLMs struggle with simple computation that decades-old technologies have succeeded at? What place do they have in pushing the frontier of what’s possible with AI #math study tools? Viraj Singh takes a look under the hood of LLMs and math #AI tools, and explores how the industry is working to improve LLM math performance in several ways: process supervision, integration with symbolic computing systems (like ChatGPT + Wolfram|Alpha), and novel ways of capturing unique and structured data (Thinkverse (formerly Learnie AI), Photomath, Sizzle, Thetawise and many others). We have some ways to go before LLM-based math tools can be accurate enough to be reliable and trustworthy. Nonetheless, they hold immense promise. Instead of simply crunching numbers, they can help process messy math problems (in both the natural language and the natural world) and aid in the communication needed to scaffold and explain the steps towards the solution. If you’re building or interested in the new frontier of AI-powered math education, read and reach out! https://lnkd.in/gGrPv_Uk

14

Researchers at Oxford Presented Policy-Guided Diffusion: A Machine Learning Method for Controllable Generation of Synthetic Trajectories in Offline Reinforcement Learning RL Quick read: https://lnkd.in/g3DdUCgj Researchers from Oxford University present policy-guided diffusion (PGD) to address the issue of compounding error in offline RL by modeling entire trajectories rather than single-step transitions. PGD trains a diffusion model on the offline dataset to generate synthetic trajectories under the behavior policy. To align these trajectories with the target policy, guidance from the target policy is applied to shift the sampling distribution. This results in a behavior-regularized target distribution, reducing divergence from the behavior policy and limiting generalization error. PGD utilizes a trajectory-level diffusion model trained on an offline dataset to approximate the behavior distribution. Inspired by classifier-guided diffusion, PGD incorporates guidance from the target policy during the denoising process to steer trajectory sampling toward the target distribution. This results in a behavior-regularized target distribution, balancing action likelihoods under both policies. PGD excludes behavior policy guidance, focusing solely on target policy guidance. To control guidance strength, PGD introduces guidance coefficients, allowing for fine-tuning of the regularization level towards the behavior distribution. Also, PGD applies a cosine guidance schedule and stabilization techniques to enhance guidance stability and reduce dynamic error. Paper: https://lnkd.in/g3JZDBAP #artificialintelligence University of Oxford #ai

22

The paper (2020) by Jared Williard et al on ‘Integrating Physics-based modeling with machine learning’ makes for an insightful read. ⬇️ What they provide through this paper are the objectives of Physics-#ML integration, which clearly are: 👉 finding computationally inexpensive representations of more complex #models 👉 discovering governing equations 👉 solving PDEs 👉 uncertainty quantification 👉 #data generation Physics-based approaches for #data generation often rely on running physical simulations or experiments, which tend to be very time consuming. Also, they are restricted by what can be produced by only physics-based #models. Hence there is an increasing interest in deep learning #DL approaches. Neural network approaches like #GAN, #VAE learn #data distributions in unsupervised settings and have the potential to generate new #data beyond what could be produced by traditional approaches. The generative adversarial network #GAN is one #DL architecture that extracts representative latent embeddings from observed #data distributions; #DL methods are known to approximate distributions very well. The #data generated by capturing latent embeddings are similar to observed #data. The adversarial component of #GAN consists of a 2-part framework namely, generative network and discriminative network; the generator’s objective is to generate sample #data and the discriminator determines if the sample came from training/observed #data or the generator. The generative and discriminative networks thus compete against each other and a #GAN learns to generate new samples.

5

1 Comment

Join us as we sit down with Ernest Chan—physicist-turned-quant, author, and founder of PredictNow.ai. In this episode, Dr. Chan shares invaluable insights on building robust data pipelines, engineering predictive signals, and choosing the right ML models for live trading. We also dive into practical risk management techniques, dynamic position sizing, and the role of AI agents in asset management. https://lnkd.in/gSikSjxc 

55

4 Comments

Introduction to Math AI With a Case Study Towards Instantaneous Calculation of Densities of SDEs From Their Parameters Context We have been working with Hermite series/Z-series representation of densities for at least three years now. Using Hermite-Series/Z-series, we can represent a very large class of densities extremely faithfully with just 6-8 coefficients of the respective series. Most of the densities we come across in finance including Generalized Gamma density, most non-central chi-squared type densities, lognormal densities and large class of densities that are similar but cannot be described by three parameter classic distributions, can easily be captured using just 6-8 coefficients of respective Z-series/Hermite Series. There might be some exceptions when higher moments of some of these densities might be too large and then we might need to represent them with ten coefficients of the Z-series/Hermite-Series for example when variance of lognormal densities is too high. At any time along their evolution, densities of most SDEs that we usually encounter in finance can easily be captured by a Hermite-series/Z-series described only by six to eight coefficients. Please Read Full Post Here: https://lnkd.in/dGt2VFjJ #AI #ML #DeepAI

1