Jay Shah

Phi-ML meets Engineering: Thermodynamic Computation and Applications to Machine Learning https://lnkd.in/ePrhJ4dm Thermodynamic hardware represents a novel computing paradigm where a noise-aware analog device is used as a resource for computation. The time evolution of such analog circuits is well-described by stochastic differential equations and can subsequently utilised for linear algebra primitives. We describe rigorous computational speedups over established digital algorithms as well as application to large scale machine learning training through thermodynamic natural gradient descent. We also present experimental results confirming the theoretical framework of thermodynamic computing. Finally, we explore its connections to uncertainty quantification and machine learning through our open-source library posteriors.

8

Robust determination of cubic elastic constants via nanoindentation and Bayesian inference https://lnkd.in/gEcRgQJq

5

Effect of Correlated Errors on Quantum Memory Smita Bagewadi, Avhishek Chatterjee https://lnkd.in/es4_QN4c Recent improvements in LDPC code based fault-tolerance for memory against i.i.d. errors naturally lead to the question of fault-tolerance against errors with long-range correlations. We introduce a classical correlation model based on hidden random fields for modeling such errors. We show that this proposed model can capture certain correlation patterns not captured by the joint (system and bath) Hamiltonian model with pairwise terms. Towards that, we derive a converse result for retention time in the presence of an error distribution, which is from the proposed class and exhibits quadratically small correlations. On the other hand, we show that for a broad subclass of error distributions within the proposed model, Tanner codes can ensure exponential retention time when the error rate is sufficiently low. The proposed model is analytically tractable due to the existence of a rich probability literature and thus, can offer insights complementary to the joint Hamiltonian model with pairwise terms.

3

A session on "Julia Compiler Secrets - Static Analysis" by Keno Fischer and Shuhei Kadowaki The Julia compiler has evolved significantly, expanding its static analysis capabilities beyond type inference to include effect analysis, escape analysis, and optimized generics. These advancements, introduced in recent releases like Julia 1.8 and 1.11, are paving the way for faster, more efficient, and safer code. The talk delved into how these new capabilities enhance code performance and correctness, offering insights into the future of the Julia compiler. Exciting times ahead for Julia developers #JuliaCon #JuliaLang #CompilerTech #StaticAnalysis #PerformanceOptimization

75

This week's Tuesday Tutorial takes our exploration of neural networks to the next level by applying them to Universal Differential Equations: https://lnkd.in/gbyZfBUU. In this installment, we generate data and train a neural net to partially learn a Lotka-Voltera system using Collimator. #controlsystems #controlsengineering #controltheory #smartsystems #engineering #python #JAX #collimator #simulation #technology #machinelearning #ml #ai

22

The next honorable mention for the 2023 IEEE Transactions on #Robotics King-Sun Fu Memorial Best Paper Award is a paper we shared several months ago. Paper title: Kinegami: Algorithmic Design of Compliant Kinematic Chains From Tubular Origami Authors: Wei-Hsi Chen , Woohyeok Yang, Lucien Peach, Daniel E. Koditschek GRASP, and Cynthia Sung Paper link: https://lnkd.in/ggRQ7cQf Video caption: The supplemental video presents the introduction, fabrication, and application of a catalog of tubular origami modules and their compositions. It also shows an animated description of the "Kinegami" algorithm and includes a demonstration of an actuated Kinegami catapult. #RobotKinematics #Actuators #OrigamiRobot

165

2 Comments

🚀 Preparing for GATE 2025? Dive into Engineering Mathematics with this comprehensive resource! 📘 🌐 Check out the Engineering Mathematics for GATE 2025 repository on GitHub! It’s packed with study material, practice problems, and helpful resources tailored for GATE aspirants. 🔗 GitHub Repository: https://lnkd.in/dXswA65A Whether you’re revising or tackling new concepts, this repo is designed to help you succeed! Good luck, and let’s ace GATE 2025 together! 💪📈 #GATE2025 #EngineeringMathematics #GATEPreparation #StudyResources #EngineeringStudents #CompetitiveExams #GitHub #GATEAndTech

4

'𝘔𝘢𝘯𝘺 𝘣𝘰𝘰𝘬𝘴 𝘢𝘯𝘥 𝘰𝘯𝘭𝘪𝘯𝘦 𝘳𝘦𝘴𝘰𝘶𝘳𝘤𝘦𝘴 𝘢𝘳𝘦 𝘴𝘵𝘪𝘭𝘭 𝘵𝘦𝘢𝘤𝘩𝘪𝘯𝘨 𝘰𝘭𝘥𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘧 𝘾++, 𝘵𝘩𝘦𝘳𝘦𝘣𝘺 𝘳𝘦𝘴𝘵𝘳𝘪𝘤𝘵𝘪𝘯𝘨 𝘺𝘰𝘶 𝘧𝘳𝘰𝘮 𝘳𝘦𝘢𝘭𝘪𝘻𝘪𝘯𝘨 𝘵𝘩𝘦 𝘭𝘢𝘯𝘨𝘶𝘢𝘨𝘦’𝘴 𝘱𝘰𝘵𝘦𝘯𝘵𝘪𝘢𝘭 𝘵𝘰 𝘵𝘩𝘦 𝘧𝘶𝘭𝘭𝘦𝘴𝘵', says Kris van Rens. C++ has evolved a lot over time. In his “C++ fundamentals” training at High Tech Institute, computer programming enthusiast Kris van Rens introduces C++20, including topics like templates and ranges. Read the interview and check out the training now: https://lnkd.in/etGJDY7G #softwareengineering #modernC++ #computerprogramming

6

1 Comment

🤖 Learn how to build a state-of-the-art chatbot application optimized for mobile processors, using tools like the OpenVINO™ Toolkit and PyTorch with Paula Ramos, PhD during her session at #AllThingsOpen happening today at 1:45pm.

42

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

If you are at #ISC24 and interested in parallel programming, follow the presentation of Suyash Tandon, Ph.D. on "Porting HPC Applications to AMD Instinct MI300A Using Unified Memory and #OpenMP" The combination of OpenMP and Unified Memory is a very interesting option for programming heterogeneous systems! Time: 2:20 - 2:45 pm Hall F - 2nd floor #HPC #Embedded

22

Here is our new paper accepted in Neurocomputing journal. SITU: Stochastic input encoding and weight update thresholding for efficient memristive neural network in-situ training The Analog-to-Digital Converter (ADC) sensing and conductance update are the most power-demanding processes in the in-situ training of memristive neural networks. In this work, we propose a new thresholded weight update method in conjunction with stochastic input encoding to reduce the ADC sensing requirement and weight updates. This leads to better power and area efficiency for simple neural network models developed in situ on memristive crossbars. This is an interesting research work by Xuening Dong and collaboration between University of Toronto, James Cook University , and York University. https://lnkd.in/gY4-GgtC

58

1 Comment

vGPU, MIG, & Time-Slicing! 3 ways to optimize the #GPU resources to meet the dynamic demands of computational tasks💻 In this article, Sameer Kulkarni explains & compares them so you can make the best choice for better GPU optimization👇 https://lnkd.in/gFQPX4b4

19