Deeplearning4j Documentation
Posted by Armando Brito Mendes | Filed under materiais para profissionais, software
clique na imagem para seguir o link
O site de um pacote java para deeplearing com montes de info. sobre redes neuronais e afins.
- How To
- Quickstart: Running Examples and DL4J in Your Projects
- Comprehensive Setup Guide
- Build Locally From Master
- Contribute to DL4J (Developer Guide)
- Choose a Neural Net
- Use the Maven Build Tool
- Vectorize Data With Canova
- Build a Data Pipeline
- Run Benchmarks
- Configure DL4J in Ivy, Gradle, SBT etc
- Find a DL4J Class or Method
- Save and Load Models
- Interpret Neural Net Output
- Visualize Data with t-SNE
- Swap CPUs for GPUs
- Customize an Image Pipeline
- Perform Regression With Neural Nets
- Troubleshoot Training & Select Network Hyperparameters
- Visualize, Monitor and Debug Network Learning
- Speed Up Spark With Native Binaries
- Build a Recommendation Engine With DL4J
- Use Recurrent Networks in DL4J
- Build Complex Network Architectures with Computation Graph
- Train Networks using Early Stopping
- Download Snapshots With Maven
- Customize a Loss Function
- Introduction to Neural Networks
- Multilayer Neural Nets
- Tutorials
- Datasets
- Scaleout
- Text
- Resources
- DL4J, Torch7, Theano and Caffe
- Glossary of Terms for Deep Learning and Neural Nets
- Deep Learning’s Accuracy
- DataVec: ETL for ML
- ND4J Backends: How They Work
- Model Zoo
- Unsupervised Learning: Use Cases
- Eigenvectors, PCA, Covariance and Entropy
- Thought Vectors, AI and NLP
- Questions to Ask When Applying DL
- AI, Machine Learning and Deep Learning
- DL and Reinforcement Learning
- Javadoc: DL4J Methods and Classes
- Canova Javadoc: Canova Methods and Classes
- ND4J User Guide
- ND4J Javadoc
- Scala, Spark and Deep Learning
- Further Reading on Deep Learning
- Deep Learning in Other Languages
- Use Cases
- Architecture
- Features
- Roadmap
- About
- Open Data
- Latest Release Notes
Guardar
Tags: análise de dados, big data, data mining, desnvolvimento de software, machine learning
The Many Faces of ROC Analysis
Posted by Armando Brito Mendes | Filed under materiais para profissionais
clicar na imagem para seguir o link
Bom tutorial sobre curvas ROC
Receiver Operating Characteristics (ROC) Analysis originated from signal detection theory, as a model of how well a receiver is able to detect a signal in the presence of noise. Its key feature is the distinction between hit rate (or true positive rate) and false alarm rate (or false positive rate) as two separate performance measures. ROC analysis has also widely been used in medical data analysis to study the effect of varying the threshold on the numerical outcome of a diagnostic test. It has been introduced to machine learning relatively recently, in response to classification tasks with varying class distributions or misclassification costs (hereafter referred to as skew). ROC analysis is set to cause a paradigm shift in machine learning. Separating performance on classes is almost always a good idea from an analytical perspective. For instance, it can help us to
- understand the behaviour and skew-sensitivity of many machine learning metrics, including rule learning heuristics and decision tree splitting criteria, by plotting their isometrics in ROC space;
- develop new metrics specifically designed to improve the Area Under the ROC Curve (AUC) of a model;
- understand fundamental algorithms such as the separate-and-conquer or sequential covering rule learning algorithm, by tracing its trajectory through a sequence of ROC spaces.
The goal of this tutorial is to develop the ROC perspective in a systematic way, demonstrating the many faces of ROC analysis in machine learning.
Tags: data mining, DW \ BI, machine learning
Best Data Science Learning podcasts
Posted by Armando Brito Mendes | Filed under lições, materiais ensino, materiais para profissionais, videos
Muito bons podcasts tem temas introdutórios
We present the top 12 Data Science & Machine Learning related Podcasts by popularity on iTunes. Check out latest episodes to stay up-to-date & become a part of the data conversations!
By Bhavya Geethika Peddibhotla.
Learn Data science the new way by listening to these compelling story tellers, interviewers, educators and experts in the field. Data suggests that podcasting about Data Science is only growing!
Tags: análise de dados, big data, data mining, desnvolvimento de software, Estat Descritiva, machine learning
Theoretical Motivations for Deep Learning
Posted by Armando Brito Mendes | Filed under lições
clicar na imagem para seguir o link
Uma boa introdução ao Deep Learning uma nova técnica de machine learning.
This post is based on the lecture “Deep Learning: Theoretical Motivations” given by Dr. Yoshua Bengio at Deep Learning Summer School, Montreal 2015. I highly recommend the lecture for a deeper understanding of the topic.
Deep learning is a branch of machine learning algorithms based on learning multiple levels of representation. The multiple levels of representation corresponds to multiple levels of abstraction. This post explores the idea that if we can successfully learn multiple levels of representation then we can generalize well.
Tags: data mining, machine learning
