Sun.Jun 30, 2024

article thumbnail

How to Build a Multilingual Chatbot using Large Language Models?

Analytics Vidhya

Introduction This article covers the creation of a multilingual chatbot for multilingual areas like India, utilizing large language models. The system improves consumer reach and personalization by using LLMs to translate questions between local languages and English. We go over the architecture, implementation specifics, advantages, and required actions.

Analytics 349
article thumbnail

Stable Diffusion Project: Reviving Old Photos

Machine Learning Mastery

Photography has been around for more than a century. There are many old photos around, and probably your family has some, too. Limited by the camera and film of the time, you may have photos of low resolution, blurry, or with folds or scratches. Restoring these old photos and making them like new ones taken […] The post Stable Diffusion Project: Reviving Old Photos appeared first on MachineLearningMastery.com.

207
207
professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

Google Arts and Culture site I didn't know existed

Hacker News

Google Arts & Culture features content from over 2000 leading museums and archives who have partnered with the Google Cultural Institute to bring the world's treasures online.

182
182
article thumbnail

Optimization Without Retraction on the Random Generalized Stiefel Manifold

Machine Learning Research at Apple

Optimization over the set of matrices X that satisfy X^TBX = Ip, referred to as the generalized Stiefel manifold, appears in many applications involving sampled covariance matrices such as the canonical correlation analysis (CCA), independent component analysis (ICA), and the generalized eigenvalue problem (GEVP). Solving these problems is typically done by iterative methods that require a fully formed B.

130
130
article thumbnail

Optimizing The Modern Developer Experience with Coder

Many software teams have migrated their testing and production workloads to the cloud, yet development environments often remain tied to outdated local setups, limiting efficiency and growth. This is where Coder comes in. In our 101 Coder webinar, you’ll explore how cloud-based development environments can unlock new levels of productivity. Discover how to transition from local setups to a secure, cloud-powered ecosystem with ease.

article thumbnail

Self-healing 'living skin' can make robots more humanlike

Hacker News

A combination of cultured cells and silicone could help robots appear more human in future thanks to realistic skin elasticity. And they can smile like us too.

181
181
article thumbnail

Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection

Machine Learning Research at Apple

The inability to linearly classify XOR has motivated much of deep learning. We revisit this age-old problem and show that linear classification of XOR is indeed possible. Instead of separating data between halfspaces, we propose a slightly different paradigm, equality separation, that adapts the SVM objective to distinguish data within or outside the margin.

More Trending

article thumbnail

Applying RLAIF for Code Generation with API-usage in Lightweight LLMs

Machine Learning Research at Apple

This paper was accepted at the Natural Language Reasoning and Structured Explanations workshop at ACL 2024. Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains, including mitigating harm in LLM outputs, enhancing text summarization, and mathematical reasoning. This paper introduces an RLAIF framework for improving the code generation abilities of lightweight (<1B parameters) LLMs.

AI 130
article thumbnail

DOJ to offer Boeing "sweetheart" plea deal in pursuit of criminal charges

Hacker News

The US Justice Department is nearing an agreement with Boeing that would include a corporate monitor and a fine in exchange for a guilty plea to criminal charges — an offer the lawyer representing the families of victims of two fatal 737 Max crashes harshly rebuked as a “sweetheart deal.

165
165
article thumbnail

How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad

Machine Learning Research at Apple

Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch? Recent works show that Transformers can be Turing-complete in terms of expressivity, but this does not address the learnability objective. This paper puts forward the notion of distribution locality to capture when weak learning is efficiently achievable by regular Transformers, where the locality measures the least number of tokens required in a

130
130
article thumbnail

Boeing Agrees to Buy Spirit AeroSystems, a Longtime Supplier

Hacker News

The multibillion-dollar deal will reverse a decision the plane maker made two decades ago to outsource production of key parts to independent suppliers.

181
181
article thumbnail

15 Modern Use Cases for Enterprise Business Intelligence

Large enterprises face unique challenges in optimizing their Business Intelligence (BI) output due to the sheer scale and complexity of their operations. Unlike smaller organizations, where basic BI features and simple dashboards might suffice, enterprises must manage vast amounts of data from diverse sources. What are the top modern BI use cases for enterprise businesses to help you get a leg up on the competition?

article thumbnail

How I built my own custom 8-bit Quantizer from scratch: a step-by-step guide using PyTorch

Towards AI

Last Updated on June 30, 2024 by Editorial Team Author(s): Milan Tamang Originally published on Towards AI. A step-by-step approach to build custom 8-bit quantizers from scratch using PyTorch and quantize facebook/opt-350m. Image by writer: MYQ (My Quantizer) quantizes the Facebook/opt-350 model and reduces the size by 54% Are you curious how popular quantizers such as BitsAndBytes, AWQ, and GGUF work under the hood?

Algorithm 101
article thumbnail

MIT robotics pioneer Rodney Brooks thinks people are vastly overestimating AI

Hacker News

Robotics pioneer Rodney Brooks thinks people are overestimating generative AI's capabilities and it's time to put the brakes on the hype.

AI 182
article thumbnail

Single Vs Multi-Task LLM Instruction Fine-Tuning

Towards AI

Author(s): Youssef Hosni Originally published on Towards AI. The comparative advantages and challenges of single-task versus multi-task fine-tuning of large language models (LLMs) are explored. The discussion begins with single-task fine-tuning, highlighting its benefits and drawbacks, including the issue of catastrophic forgetting. It then transitions to an overview of multitasking fine-tuning, examining both its challenges and potential benefits.

AI 82
article thumbnail

Can a law make social media less 'addictive'?

Hacker News

New York just passed a law on "addictive" social media feeds for children, but some researchers are questioning what that actually means.

181
181
article thumbnail

The Cloud Development Environment Adoption Report

Cloud Development Environments (CDEs) are changing how software teams work by moving development to the cloud. Our Cloud Development Environment Adoption Report gathers insights from 223 developers and business leaders, uncovering key trends in CDE adoption. With 66% of large organizations already using CDEs, these platforms are quickly becoming essential to modern development practices.

article thumbnail

Bridging the Implementation Gap of Artificial Intelligence in Healthcare

Towards AI

Author(s): Eera Bhatt Originally published on Towards AI. Each year, we spend so much time and money developing new machine learning models, but most of them never get used in a practical setting. Sadly, this issue is even worse in the healthcare industry. Photo by Testalize.me on Unsplash A.I. in medicine. Because of COVID-19, a lot of us know about AI and are also familiar with its applications in medicine, but let’s summarize them for anyone who needs it.

article thumbnail

WhatsApp Android beta reveals Llama 3 405B option

Hacker News

Discover what's new in the WhatsApp beta for Android 2.24.14.7 update: WhatsApp is working on a feature to choose the Meta AI Llama model!

AI 172
article thumbnail

Auto-Streamlit Studio

Towards AI

Last Updated on June 30, 2024 by Editorial Team Author(s): Stavros Theocharis Originally published on Towards AI. Introduction In the rapidly evolving landscape of web application development and artificial intelligence, having the right tools at your disposal can significantly streamline your workflow and boost productivity. Enter AutoStreamlit Studio, an intelligent assistant designed to simplify the creation of Streamlit applications.

article thumbnail

Goldman Sachs says the return on investment for AI might be disappointing

Hacker News

Tech companies are spending big on AI, but so far have little to show for it. A Goldman Sachs report gives AI investments mixed reviews.

AI 178
article thumbnail

Marketing Operations in 2025: A New Framework for Success

Speaker: Mike Rizzo, Founder & CEO, MarketingOps.com and Darrell Alfonso, Director of Marketing Strategy and Operations, Indeed.com

Though rarely in the spotlight, marketing operations are the backbone of the efficiency, scalability, and alignment that define top-performing marketing teams. In this exclusive webinar led by industry visionaries Mike Rizzo and Darrell Alfonso, we’re giving marketing operations the recognition they deserve! We will dive into the 7 P Model —a powerful framework designed to assess and optimize your marketing operations function.

article thumbnail

De-Mystifying Embeddings

Towards AI

Last Updated on June 30, 2024 by Editorial Team Author(s): Shashank Bhushan Originally published on Towards AI. Understanding What Embeddings Are Embeddings, sometimes also referred to as Feature representation, are a widely used technique/concept in Neural Network based machine learning. They are usually taken from an intermediate or hidden layer of a Deep Neural Network.

ML 66
article thumbnail

How Google migrated billions of lines of code from Perforce to Piper

Hacker News

In 2011, Dan Bloch, the tech lead on the Perforce admin team at Google, published “Still All On One Server: Perforce at Scale[link].” The paper described how Google’s source control system, servicing “over twelve thousand users” a day, still ran off of a single Perforce server, tucked away under a stairwell in Building 43 on its main campus.

146
146
article thumbnail

War Can’t Stop Israeli Startups Determined To Thrive In The Desert

Gil Press for Forbes

Israeli startups BionicHIVE and Carrar, managed by people that defy the odds, are based in the town of Sderot, located less than a mile from Gaza.

article thumbnail

Unification in Elixir

Hacker News

Pattern matching is a pervasive and powerful tool in Elixir. This isn't too surprising if you know a little about the history of Elixir's parent language, Erlang. Erlang was originally inspired by and written in Prolog, a logic programming language where pattern matching has first-class support.

144
144
article thumbnail

Introducing CDEs to Your Enterprise

Explore how enterprises can enhance developer productivity and onboarding by adopting self-hosted Cloud Development Environments (CDEs). This whitepaper highlights the simplicity and flexibility of cloud-based development over traditional setups, demonstrating how large teams can leverage economies of scale to boost efficiency and developer satisfaction.

article thumbnail

Commercial vs. Self-Hosted LLMs: A Cost Analysis & How to Choose the Right Ones for You

Iguazio

As can be inferred from their name, foundation models are the foundation upon which developers build AI applications for tasks like language translation, text summarization, sentiment analysis and more. Models such as OpenAI's GPT, Google's Gemini, Meta’s Llama and Anthropic’s Claude, are pre-trained on vast amounts of text data and have the capability to understand and generate human-like language.

ML 105
article thumbnail

Automating my gate door via a smart relay

Hacker News

How to automate a gate door without remote capabilities using a smart relay and integrate it into HomeKit via Home Assistant.

181
181
article thumbnail

Commercial vs. Self-Hosted LLMs: A Cost Analysis & How to Choose the Right Ones for You

Iguazio

As can be inferred from their name, foundation models are the foundation upon which developers build AI applications for tasks like language translation, text summarization, sentiment analysis and more. Models such as OpenAI's GPT, Google's Gemini, Meta’s Llama and Anthropic’s Claude, are pre-trained on vast amounts of text data and have the capability to understand and generate human-like language.

ML 95
article thumbnail

Chaos Engineering in Front End Development: Enhancing Application Resilience

Hacker News

In the dynamic world of web development, ensuring the resilience and reliability of frontend applications has become increasingly critical. As user expectations soar and application complexity grows, developers must adopt robust strategies to maintain high-quality, fault-tolerant systems. Enter Chaos Engineering – a discipline traditionally associated with backend systems and infrastructure, now making significant inroads into frontend development.

137
137
article thumbnail

Prepare Now: 2025s Must-Know Trends For Product And Data Leaders

Speaker: Jay Allardyce, Deepak Vittal, and Terrence Sheflin

As we look ahead to 2025, business intelligence and data analytics are set to play pivotal roles in shaping success. Organizations are already starting to face a host of transformative trends as the year comes to a close, including the integration of AI in data analytics, an increased emphasis on real-time data insights, and the growing importance of user experience in BI solutions.

article thumbnail

Weavers and Concluders: Two communication styles (2021)

Hacker News

People expect that we all have the same communication instincts, but there are at least two communication styles that, without knowledge of them, will result in a lifetime of missed connections.

136
136
article thumbnail

Quaternions in Signal and Image Processing

Hacker News

Quaternions are still largely misunderstood and often considered an “exotic” signal representation without much practical utility despite the fact that they have been around the signal and image processing community for more than 30 years now. The main aim of this article is to counter this misconception and to demystify the use of quaternion algebra for solving problems in signal and image processing.

136
136
article thumbnail

Userland rootkits are lame (2022)

Hacker News

Many people may not know this, but fifteen…twenty years ago I knew a thing or two about rootkit development. I wrote detection software for a few years as well. Back then modifying the shared libraries on the disk was also vector for userland rootkits.

136
136
article thumbnail

Hoping for a Miracle to Save the Ogallala Aquifer? Prepare for the New Dust Bowl

Hacker News

No rainmaker, no aqueduct, and no prayer will save western Kansas from the depletion of the Ogallala Aquifer.

182
182
article thumbnail

How to Drive Cost Savings, Efficiency Gains, and Sustainability Wins with MES

Speaker: Nikhil Joshi, Founder & President of Snic Solutions

Is your manufacturing operation reaching its efficiency potential? A Manufacturing Execution System (MES) could be the game-changer, helping you reduce waste, cut costs, and lower your carbon footprint. Join Nikhil Joshi, Founder & President of Snic Solutions, in this value-packed webinar as he breaks down how MES can drive operational excellence and sustainability.