Deep Learning Illustrated: A Visual, Interactive Guide to Artificial IntelligenceAddison-Wesley Professional, 2019 M08 5 - 416 páginas "The authors’ clear visual style provides a comprehensive look at what’s currently possible with artificial neural networks as well as a glimpse of the magic that’s to come." – Tim Urban, author of Wait But Why Fully Practical, Insightful Guide to Modern Deep Learning Deep learning is transforming software, facilitating powerful new artificial intelligence capabilities, and driving unprecedented algorithm performance. Deep Learning Illustrated is uniquely intuitive and offers a complete introduction to the discipline’s techniques. Packed with full-color figures and easy-to-follow code, it sweeps away the complexity of building deep learning models, making the subject approachable and fun to learn. World-class instructor and practitioner Jon Krohn–with visionary content from Grant Beyleveld and beautiful illustrations by Aglaé Bassens–presents straightforward analogies to explain what deep learning is, why it has become so popular, and how it relates to other machine learning approaches. Krohn has created a practical reference and tutorial for developers, data scientists, researchers, analysts, and students who want to start applying it. He illuminates theory with hands-on Python code in accompanying Jupyter notebooks. To help you progress quickly, he focuses on the versatile deep learning library Keras to nimbly construct efficient TensorFlow models; PyTorch, the leading alternative library, is also covered. You’ll gain a pragmatic understanding of all major deep learning approaches and their uses in applications ranging from machine vision and natural language processing to image generation and game-playing algorithms.
|
Otras ediciones - Ver todas
Deep Learning Illustrated: A Visual, Interactive Guide to Artificial ... Jon Krohn,Grant Beyleveld,Aglaé Bassens Sin vista previa disponible - 2019 |
Términos y frases comunes
accuracy activation function activation map activation='relu adversarial network AlexNet algorithm artificial neural network artificial neurons backpropagation batch bigrams calculate Cart-Pole game Chapter Click computational Conv2D convolutional layers corpus cross-entropy cost deep learning models deep reinforcement learning DeepMind dense layer dense network DQN agent dropout environment episode Equation Example Figure filter forward propagation Glorot hidden layer hot dog hyperparameters Jupyter notebook Keras keras.layers import kernel learning rate LeNet-5 LSTM machine learning machine vision MNIST digits model architecture model.add model.add(Dense natural language processing NumPy one-hot OpenAI Gym optimal output layer overfitting PAD PAD PAD parameters percent perceptron pixels predict preprocessing PyTorch Q-learning R-CNN ReLU representations ROC AUC Sequential sigmoid softmax stochastic gradient descent supervised learning TensorBoard TensorFlow timestep traditional machine learning training data trilobite UNK UNK validation values vector space view code image visual weight initialization word vectors word-vector space word2vec y_train y_valid