Unsupervised learning by competing hidden units | PNAS
a question remains to what extent the computational properties of deep neural networks are similar to those of the human brain. The particularly nonbiological aspect of deep learning is the supervised training process with the backpropagation algorithm, which requires massive amounts of labeled data, and a nonlocal learning rule for changing the synapse strengths. This paper describes a learning algorithm that does not suffer from these two problems. It learns the weights of the lower layer of neural networks in a completely unsupervised fashion. The entire algorithm utilizes local learning rules which have conceptual biological plausibility.
deeplearning  neuralnetworks  hopfield 
8 days ago
wikidetox/wikiconv at master · conversationai/wikidetox
For the English language dataset, this results in 8.7M rows (conversations with comments from at least two distinct users).
dataset  wikipedia  conversation  corpus  dialogue  talk 
9 days ago
Introducing Transcend: Tech for the Modern Privacy Era
Data Privacy Infrastructure (DPI): Plug and play privacy management for companies
13 days ago
Biotechnology 101 Kit | Bento Lab
1 Starter Kit contains all the materials you need when learning to use Bento Lab for the first time, including instructions and reagents. Go from learning key techniques, to genetic analysis, to discussing questions of bioethics and scientific responsibility. You can go through the Biotechnology 101 Kit on your own – or even better, together with a friend.
biology  genetics  kate 
13 days ago
Stanford University Nike Tennis Camp, Paul Goldstein Sessions
These camps are geared towards boys & girls of all ability levels, ages 9-18. With a perfect mix of drills, match-play, conditioning, strategy and off-court fun, campers immerse themselves within the sport and campus, creating memories to last a lifetime. Upon arrival, all participants are evaluated by the staff so that their own instructional needs can be addressed throughout the week.
tennis  summercamp  grade4  kate 
7 weeks ago
Summer Immersion Program - Girls Who Code
Our Summer Immersion Program is a free​ ​7-week introductory computer science ​program ​for​ ​10th-11th grade girls going into their junior or senior year of high school. During the 7-week program, participants​ ​learn​ about ​computer science,​ ​gain​ ​exposure​ ​to​ ​tech​ ​jobs,​ ​and​ ​join​ ​a​ sisterhood​ ​of​ ​girls​ ​who​ ​are​ ​using​ ​computer​ ​science​ ​to​ ​become​ ​change-makers. Learn more below!
10thgrade  kate  coding  stanford 
7 weeks ago
The ML Surprise – The Launchpad – Medium
zation at a rate unmatched by software infrastructure for brute force data collection and management. Like the broccoli ice cream — there is usually not that much ML in an end-to-end ML system.

Secondly, the path of implementing ML (asking questions about your customers, building infrastructure to collect, interpret and act upon that data, etc.) is valuable, regardless of whether or not ML is actually implemented in the end. Not every problem has an ML-powered solution, but many do, and even those that do not will benefit from this jour
enterprise  enterpriseai  productmanagement 
10 weeks ago
« earlier      
advice ai algorithm algorithms amazon analysis analytics apache api app article automation aws beowulf berkeley bigdata bioinformatics blog book books bootstrap bots business c++ capistrano cloud cluster clustering code collaborative competition computerscience conference configuration course crawler css data database datamining dataset deeplearning deployment design desk development devise distributed django ec2 economics education elasticsearch email emr enterpriseai event example extraction facebook filtering finance flask from furniture gensim geo gis git github google government graph hack hadoop heroku howto html image install ios iphone java javascript jekyll json kate keyword knowledgegraph learning lectures library linkedin links linux list location log lucene mac machinelearning management map mapreduce marketing mashup mathematics matlab matrix mechanicalturk microsoft mit mllinks mobile mpi mysql named_entity netflixprize network neuralnetwork neuroscience news next nlp nltk numpy office opensource optimization osx pagerank paper parallel people performance physics pig politics prediction presentation programming publicdata python query queryminer questions r rails ranking recommendation record_linkage redis redistributable reference research resources rest retail ruby s3 sales scalability scipy scraping screencast search security segphrase seo service sf similarity skills slack slides social socialnetwork software spark sparse spatial spec ssh stanford startup startups statistics streaming syntax tag talk tensorflow testing text textmining timeseries tips todo tool tools toread towatch transparency trends tutorial twitter ubuntu via:chl video visualization web web2.0 webservice wiki wikipedia word2vec xml yahoo

Copy this bookmark: