img

Playing Atari with Deep Reinforcement Learning

DeepMind's paper "Playing Atari with Deep Reinforcement Learning" (2013) marked a milestone in AI by demonstrating how deep Q-learning could learn to play Atari games directly from pixels. This breakthrough highlighted the potential of deep RL in complex decision-making tasks and laid the foundation for subsequent advancements in reinforcement learning algorithms.

https://arxiv.org/pdf/1312.5602

img
img

vineyarrd

Credit Suisse Group

3 months ago

Nice
img

Starkjelly07

US Based MNC, India location

3 months ago

Really interesting!
Sign in to a Grapevine account for the full experience.

Discover More

Curated from across

img

Office Gossip on

by Chanakya

indsource international

Musk launched xAI.

xAI rival of open ai chatgpt and Google bard...Have hired ex-engineers of Google deepmind, open ai, Microsoft..What's your views?

img

Indian Startups on

by Tantra

Self Employed

Future GPT is to Coding what AlphaZero is to Chess

Prediction below, open to feedback and criticism: As soon as GPT can learn programming languages through self reinforcement learning, it will become invincible and you will be able to create webapps at negligible cost by just giving it objectives. Coding as a career is likely downhill from here on. Right now, we are in the DeepBlue version of GPT. It has learned from all the code available online just like DeepBlue had all human chess moves till then as its training data. But AlphaZero learned on its own from ground up, and similarly led to AlphaGo later on. Future GPT will learn all programming languages on its own from ground up, and deliver fully functional apps at neglible cost.

img

Software Engineers on

by AGIcoming

Google

Deepmind creates AlphaGeometry: an AI system that solves Olympiad geometry problems at a level approaching a human gold-medalist

https://t.co/g3RFSoWNPP

img
img

News Discussion on

by NewsAnchor

Grapevine

OpenAI Nears Human-Level AI Reasoning, Reports Say

- OpenAI researchers believe they are close to developing AI capable of human-level reasoning, according to Bloomberg and Reuters. - The company has defined five levels of artificial general intelligence (AGI), with current systems at level 1 and nearing level 2. - A project named 'Strawberry' aims to create AI that can reason, plan, and perform deep research independently. - Rumors of a breakthrough circulated before the failed attempt to oust CEO Sam Altman in November 2023. - Despite advancements, human-level reasoning in AI remains a future goal, with debates ongoing about the feasibility of achieving AGI through current large language models. Source: Axios

img
img

Data Scientists on

by Gooner7

Goldman Sachs

This Paper will make you smarter than 90% AI Engineers

I am giving a deep overview of why this is extremely important. This paper is by the three greatest researchers in the field of AI ever. They are considered to be the godfathers of AI. This paper essentially brought deep learning into the zeitgeist of the last decade. We saw the advent of some of the greatest advancement in AI. The advancements in AI are similar to the Industrial revolution, where you could not even guess the change in the nature of jobs, society, life and the world over the next 5 years. The world is changing, so don't become a horse carriage driver now, be a steam engine engineer. Compete or get outcompeted.

Yann Lecun, Yoshua Bengio, Geoffrey Hinton

https://hal.science/hal-04206682/document

img
img

Designers on

by Shroom

Design Studio

AMA ☞ Founder of a design studio based out of Bangalore

Really excited to do this! Here's a little bit about my career: - I dropped out of college to build a design studio with 20+ people for 4 years before leaving that to start another studio. - I’ve worked across most major startups in Bangalore (not including brand names here for anonymity) - I’ve worked across brand identity design, UX/UI, social media marketing, ad films, animation/motion graphics, and 3D Happy to answer questions about design, freelancing, starting an agency/studio, the design industry, etc.

img

Software Engineers on

by TechnicallyBehind

Seed Stage Startup

Staying up to date with AI happenings (how)

There's so much happening every day. I never really like the AI/ML courses of college (lol) but want to actually try the new stuff now. What'd you say is the best way of at least knowing the basics of whatever comes up daily? I know I could just google (and I will), curious to know if y'all know of something which defines the base vocabulary needed to actually understand the daily breakthroughs. Few things I've been meaning to know more about - RLHF - Fine tuning (what and how) - LLM structure (should have kept up with LLM basics but I didn't lol, pls share stuff) - LoRA/QLoRA (?? idk lmao) - RAG (vectorisation of inputs + cosine similarity with query?) - Mamba architecture (1. what, saw on twitter, no idea) Currently downloading https://ollama.ai/ to try running llama locally. Any links/pointers/newsletter archives appreciated

img

Data Scientists on

by altGrape

Stealth

As someone in AI, which concept blew your mind away when you first learnt about it?

For me? It was GradCAM was a gamechanger at selling computer vision initiatives internally to the non-technical stakeholders. The gradCAM function computes the importance map by taking the derivative of the reduction layer output for a given class with respect to a convolutional feature map. If you have a 5 layered convolutional neural network, then you can use this against any layer and check the class activation map. The best explanation to give is: "Regions in Red are the areas of the image that the neural network is looking at to make a decision" Well to be honest, regions in red represent the class activations arising from that region but, it would be too much for normie business guys.

img