Справочник
Искать:
Videos
Курс: Applied AI with DeepLearning. Чтобы вернуться, нажмите здесь.
- A warm welcome from John Cohn, IBM Fellow Watson IoT
- Introduction - Romeo Kienzler
- Introduction - Ilja Rasin
- Introduction - Niketan Pansare
- Course Logistics
- Cloud Architectures for AI and DeepLearning
- Linear algebra
- Deep feed forward neural networks
- Convolutional Neural Networks
- Recurrent neural networks
- LSTMs
- Auto encoders and representation learning
- Methods for neural network training
- Gradient Descent Updater Strategies
- How to choose the correct activation function
- The bias-variance tradeoff in deep learning
- Intoduction to TensorFlow
- Neural Network Debugging with TensorBoard
- Automatic Differentiation
- Introduction video
- Keras overview
- Sequential models in keras
- Feed forward networks
- Recurrent neural networks
- Beyond sequential models: the functional API
- Saving and loading models
- What is SystemML (1/2)
- What is SystemML (2/2)
- PyTorch Installation
- PyTorch Packages
- Tensor Creation and Visualization of Higher Dimensional Tensors
- Math Computation and Reshape
- Computation Graph, CUDA
- Linear Model
- Introduction to Anomaly Detection
- How to implement an anomaly detector (1/2)
- How to implement an anomaly detector (2/2)
- How to deploy a real-time anomaly detector
- Introduction to Time Series Forecasting
- Stateful vs. Stateless LSTMs
- Batch Size
- Number of Time Steps, Epochs, Training and Validation
- Trainin Set Size
- Input and Output Data Construction
- Designing the LSTM network in Keras
- Anatomy of a LSTM Node
- Number of Parameters
- Training and loading a saved model
- Classifying the MNIST dataset with Convolutional Neural Networks
- Image classification with Imagenet and Resnet50
- Autoencoder - understanding Word2Vec
- Text Classification with Word Embeddings
- Run Keras Models in Parallel on Apache Spark using Apache SystemML
- Computer Vision with IBM Watson Visual Recognition
- Text Classification with IBM Watson Natural Language Classifier