Challenge: what's the best accuracy (on the published test set) you can get on fashion-MNIST in 20 epochs, using a non-pretrained model? (Any self-supervision epochs you do will count in the 20 epoch limit.)
MACHINE LEARNING
-
Semantic Search Using Transformer-Based Language Models
By
–
The significance of going from "keyword" search to "semantic" search cannot be overstated. With Transformer based language models, search results are chosen based on compatibility in meaning rather than lexical overlap. http://
deepset.ai/blog/how-to-bu
ild-a-semantic-search-engine-in-python
… -
Artificial Intelligence Reshaping Online Gaming Industry Future
By
–
The Future of Online #Games: How #ArtificialIntelligence will Shape the Industry https://
techiexpert.com/the-future-of-
online-games-how-artificial-intelligence-will-shape-the-industry/
… @techiexpert #AI #DataScience #BigData #Analytics #MachineLearning #Robots #100DaysofCode #IoT #serverless #DEVCommunity #womenwhocode #DeepLearning #DigitalTransformation -
UC Berkeley and Peking U Propose Unsupervised Contrast-Consistent Search
By
–
Finding Truth in LLMs: UC Berkeley & Peking U Propose Unsupervised Contrast-Consistent Search https://
syncedreview.com/2022/12/14/fin
ding-truth-in-llms-uc-berkeley-peking-u-propose-unsupervised-contrast-consistent-search/
… -
Fine-tuned Models Testing on Public Datasets
By
–
Interesting. What kind of data are you inferring on? Is there some publicly available data that you’re testing on? Would love to test out some of our fine-tuned models against it.
-
New Math for Machine Learning and Data Science Course Launched
By
–
New course announcement! Math for Machine Learning and Data Science. Designed to make learning AI's math easy: ∙ Linear algebra ∙ Probability & Stats
∙ Calculus Will help learners build better ML systems and pass job interviews! -
Build Image Classification Deep Learning Pipeline in 15 Lines
By
–
Image classification is hard: Complex pipelines Need expert knowledge about images Weeks to train models But it doesn’t need to be. Learn to #build & #deploy an end-to-end deep learning pipeline <15 lines of code. And it's a fun use case! https://
pbase.ai/3YrInf8 -
CICERO AI Diplomacy Game: Win Rate Against Human Players
By
–
Meta AI’s CICERO plays Diplomacy with humans, like humans. And more often than not, wins. Recently, CICERO played Diplomacy games online against 82 competitors. Can you guess CICERO’s win rate compared to that of the human players?
-
LLM Interface Enhancement: Extended Output with Top Results and Token Counts
By
–
Returning extra information Previously, the LLM only returned the most likely string Now there is a new interface to return more information: the top n strings for each input, as well as LLM specific information (h/t @0xAwill for adding the token counts you see below)
-
New abstraction enables returning generation metadata like logprobs
By
–
This abstraction also opens up the door to returning more information about each generation For example, the logprobs associated with a generation (something I know @alexgraveley would love)