The world is still digesting the lessons of TinyStories https://
arxiv.org/abs/2305.07759
RESEARCH
-
Lessons from the TinyStories AI Research Paper
By
–
-
Patrick Lewis RAG Research Augments Language Models Retrieval
By
–
Research on RAG over corpora of documents by Patrick Lewis has profoundly impacted the NLP field. At Cohere, Patrick leads the modeling team effort to augment language models with access to retrieval systems and tools.
— Cohere (@cohere) 14 janvier 2024
Learn more on Chat with RAG: https://t.co/OR1VCAcnX8 pic.twitter.com/SCyxbccI9oResearch on RAG over corpora of documents by Patrick Lewis has profoundly impacted the NLP field. At Cohere, Patrick leads the modeling team effort to augment language models with access to retrieval systems and tools. Learn more on Chat with RAG: https://
txt.cohere.com/chat-with-rag/ -
Ken’s Advice for AI Success: Curiosity and Perseverance
By
–
8. Ken's Advice for Success Ken advises maintaining curiosity, perseverance through dips, and recognizing anyone can contribute to the Al movement by practising and improving, even without a university degree. Watch the full podcast on my YouTube: https://
youtu.be/TOD9-WyWExs -
Ken’s practical data science learning journey with real-world applications
By
–
7. Learning Data Science Ken's learning journey involved practical applications, statistical analysis, linear regression, and clustering. His hands-on approach was centred around solving real-world problems.
-
Learning by Doing: Applying AI Concepts to Real Problems
By
–
5. Learning by Applying Concepts Ken emphasize the value of learning by doing. Applying abstract concepts to real problems not only reinforces understanding, but provides• tangible results. This concrete feedback loop fuels curiosity. and advancement.
-
Leveraging Conversational AI for Enhanced Critical Thinking
By
–
4. The Power of Conversation Interaction with language models like ChatGPT facilitates exploration. The back-and-forth dialogue enhances output by encouraging critical thinking. Ken views the "hallucinations" as beneficial since they force deeper questioning.
-
AI Insights from Ken Jee on Data Science and Podcast
By
–
Good morning fellow AI enthusiasts! Here are amazing AI insights from @KenJee_DS
, whom I received on the What's AI podcast a few weeks ago. #whatsai #aienthusiast #podcast #dataentry #startup #learning #ai #datascience -
Animate Anyone: Controllable Image-to-Video Character Animation
By
–
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation Hu et al.: https://
arxiv.org/abs/2311.17117 #ArtificialIntelligence #DeepLearning #MachineLearning -
Dalle-3 Text Generation Struggles Revealed by 300 Tests
By
–
Here's the problem:
Dalle-3 struggles when it comes to text generation which can be frustrating when trying to make logos for example. Over 300 tests (more robust research will need to be done) were done and this is what was found: -
Production-Ready Topic Modelling Pipeline Implementation Guide
By
–
Topic Modelling in production https://
towardsdatascience.com/topic-modellin
g-in-production-e3b3e99e4fca
… This great article by Mariya Mansurova goes over: How to build a production-ready pipeline for tagging topics and sentiment of documents How to evaluate how that pipeline is doing A good mix of both building and