KNN 알고리즘은 K-Nearest Neighbor의 약자이다. 한국어로는 K 근접 이웃이라고 한다. 머신러닝의 분류에 쓰이는 대표적이면서 간단한 알고리즘이다. 얼굴 인식, 개인 영화 추천, 단백질 및 질병 추출을 위한 유전자 데이터 패턴 식별 등에 활용된다.
Recently I try to implement RBM based autoencoder in tensorflow similar to RBMs described in Semantic Hashing paper by Ruslan Salakhutdinov and Geoffrey Hinton. It seems that with weights that were pre-trained with RBM autoencoders should converge faster. So…
這篇是2016 / 8 / 31的文章
Earlier this week, we announced the latest release of the TF-Slim library for TensorFlow, a lightweight package for defining…
What I did yesterday:• DS101X Statistical Thinking for Data Science and Analytics // completion of week 2 “Probability and Statistics I”# introduction to statistics# normal (gaussian)…
A lot of my write-up for the company I am working for, now, is still there. In the Dropbox. I joined this company as the 18th employee and I realised that we needed more experienced (they are expensive in fact) craftsman to go on, guide us in the right way. Now that we have a well formed and skilful set of people in our team, we are slowly picking…
R — The name comes from the initials of its developers Ross Ihaka and Robert Gentleman, who created R programming language for statistical analysis, graphics representation, and reporting. With the passage of time, R has diversified and entered innumerable sectors…
Thinking about how training cases constrain the weight vector for perceptron. Source
Some reviews about our architecture and our main goal.
After we published our progress report, we got some reviews about our architecure and main goal’s of the system from our advisor Asst.Prof.Dr Aykut Erdem. According to that review, we realize that we have…
Permanent capital is becoming more essential to do well in investing. The shift to passive strategies are magnifying the short-term price effects on smaller accessible float. Therefore, strategies need structure to ride these movements and test hypotheses.