deep learning conference

theoretical knowledge : UFLDL data preprocessing and http://www.cnblogs.com/tornadomeet/archive/2013/04/20/3033149.htmlData preprocessing is a very important step in deep learning! If the acquisition of raw data is the most important step in deep learning, then the preprocessing of the raw data is an important part of

In the words of Russian MYC although is engaged in computer vision, but in school never contact neural network, let alone deep learning. When he was looking for a job, Deep learning was just beginning to get into people's eyes. But now if you are lucky enough to be interviewed by Myc, he will ask you this question

models on a variety of platforms, from mobile phones to individual cpu/gpu to hundreds of GPU cards distributed systems. From the current documentation, TensorFlow supports the CNN, RNN, and lstm algorithms, which are the most popular deep neural network models currently in Image,speech and NLP. This time Google open source depth learning system TensorFlow can be applied in many places, such as speech reco

, but it also surpasses most of the non-deep learning algorithms. Because face recognition is a two classification problem, it is relatively inefficient to learn facial features, and it is easy to fit on the training set. Face recognition is a more challenging multi-classification problem, it is not easy to fit, it is more suitable to learn facial features through depth model. On the other hand, in face rec

9. Common models or methods of deep learning 9.1 autoencoder automatic Encoder One of the simplest ways of deep learning is to use the features of artificial neural networks. Artificial Neural Networks (ANN) itself are hierarchical systems. If a neural network is given, let's assume that the output is the same as the i

,callbacks=[checkpointer, History]) train () Personal experience: Feel Keras use is very convenient, at the same time the source code is very easy to read, we have to modify the algorithm, you can read the bottom of the source code, learning will not be like the bottom of the caffe so troublesome, personal feeling caffe the only advantage is that there are a lot of open model, the source code, , Keras is not the same, with Python,

Written before: busy, always in a walk stop, squeeze time, leave a chance to think. Intermittent, the study of deep learning also has a period of time, from the beginning of the small white to now is a primer, halfway to read a little article literature, there are many problems. The trip to Takayama has only just begun, and this series is designed to record the path and individual

Python vector: Import NumPy as np a = Np.array ([[[1,2],[3,4],[5,6]]) SUM0 = Np.sum (A, axis=0) sum1 = Np.sum (A, Axis=1) PR int SUM0 Print sum1 > Results: [9 12][3 7] Dropout In the training process of the deep Learning Network, for the Neural network unit, it is temporarily discarded from the network according to certain probability.Dropout is a big kill for CNN to prevent the effect of fitting. Output

Deep Learning Book recommendation, deep learning bookAI Bible Classic best-selling book in the field of deep learning! Has long ranked first in Amazon AI and machine learning boo