Category Archives: Artificial Intelligence

How to build AI Startups

ecosystem / partners long tail / corner cases (domain knowledge) intelligence vs skills when to start (neither unclear nor 100% clear) niche market (big companies don’t want to do) 1.科技产业预测的核心是在产业基础上判断规模商用时点2.超级周期是科技革命的典型特征,由一个核心技术和一系列支持技术推动形成3.人工智能革命已经发生,会和更多支持技术结合,扩散到更多领域,但时间会有先后4.近期值得关注的领域:智能服务、机器人、MR+AI Give credit to employees to use the product (Uber), eat … Continue reading

Posted in Artificial Intelligence, startup | Tagged , , , | Leave a comment

Intro to AI

AI vs ML vs DL AI (Artificial Intelligence): machine intelligence to reason, infer, interact so that others could not distinguish it with real human being. ML (Machine Learning): machine use data to learn pattern to predict, cluster. DL (Deep Learning): … Continue reading

Posted in Artificial Intelligence, CS Research&Application | Tagged , , , , , | Leave a comment

Machine Learning Concepts Cheatsheet

I – Data Modeling and Evaluation Topics 1. Data preprocessing: Munging/wrangling, transforming, aggregating, etc.  2. Pattern recognition: Correlations, clusters, trends, outliers & anomalies, etc.  3. Dimensionality reduction: Eigenvectors, Principal Component Analysis, etc.  4. Prediction: Classification, regression, sequence prediction, etc.; suitable … Continue reading

Posted in Artificial Intelligence, CS Research&Application | Tagged , | Leave a comment

Programming Concurrency on the JVM

In the weekend, I read the book Programming Concurrency on the JVM and it opens a new window for me to apply concurrency theory on the JVM with languages as Clojure, Java, JRuby and Scala. I write down essentials as … Continue reading

Posted in Artificial Intelligence, CS Research&Application | Tagged , | Leave a comment

Generative Deep Learning

Generative vs Discriminative Naive Bayes Variational Auto Encoder (VAE) / Decoder Generative Adversarial Networks (GAN) Convolution Neural Network Batch Normalization Activation (ReLU, Leaky ReLU, Sigmoid, Tanh, Softmax) Dropout Keras + TensorFlow Paint, Compose, Write, Play   Donate $5 to me … Continue reading

Posted in Artificial Intelligence, Uncategorized | Tagged , | Leave a comment

Deep Learning Notes – Activation Function

Activation function Sigmoid: Vanishing gradient (but still used in RNN. gradient for multi-D and slope for 1-D) ReLU:sub differential (corner point could be derivative) Tanh: (range from negatives)   Train model and learn parameters to minimize loss   Loss function … Continue reading

Posted in Artificial Intelligence, Uncategorized | Tagged , | Leave a comment

AI Serving

1. Serving End to end system (given input and provide output, accept request and give response) AI serving (using AI technique to provide response for request)   2. Traditional Web Application Whole page reload when direct to other pages   … Continue reading

Posted in Artificial Intelligence, Uncategorized | Tagged , | Leave a comment