1. What is LSTM, BiLSTM and when to use them?
  2. How to extract specific information from raw , unstructured text using NLP and Deep Learning?

  3. Does gradient descent always converge to an optimum?

  4. Classification of obfuscated text data

  5. Autoencoder behavior with All White/Black MNIST

  6. Adding Features To Time Series Model LSTM

  7. Help with the following error: Variable already exists, disallowed. Did you mean to set reuse=True in VarScope?

  8. Keras - no prediction probability for multiple output models?
  9. Input normalization for ReLu?
  10. Recognition of Geometric shapes for ridges

  11. Incorporate luck in statistical modelling

  12. Using an autoencoder to mimic independent component analysis?

  13. Solving classification task with deep network

  14. LSTM in R: How to interpret output?

  15. Explain Binary Classification with output 0.5 (True)

  16. Point symmetric recurrent neural network

  17. Some questions about GoogleNet paper
  18. NLP for appartement ads

  19. What it Would be easier Building a Deep Net From Scratch or Using an existing Architecture?
  20. Updating the weights of the filters in a CNN
  21. Can dropout and batch normalization be applied to convolution layers
  22. What is the purpose of untrainable weights in Keras

  23. Multi GPU in keras
  24. How to make unstructured data to structured data?

  25. How to think about prediction error that is not convex in hyperparameter, or over the course of training

  26. Keyword extraction using deep learning
  27. How do you train a machine learning model to learn how to adjust images (contrast, brightness, saturation, crop etc.) from manually adjusted images?
  28. Tensorflow Train Cnn on Multi-Gpu With Dataset api Does Not work

  29. what does smooth/soft probablity mean?

  30. Understanding Tensorflow LSTM models?

  31. Building CNN, Need More Images
  32. MxNet version of Keras MLP doesn't learn
  33. How to Precondition A Fully Convolutional Neural Network

  34. How to retrain the neural network when new data comes in?
  35. Can we generate huge dataset with Generative Adversarial Networks
  36. Gradient flow through concatenation operation
  37. Keyword Extraction and Document Clustering in Deep learning
  38. Effect on feature map for separately training multi label image classification

  39. What is the classical way to visualize 3D filters in convolutional neural networks?
  40. Implementing a CNN with one convolution layer
  41. Machine-learning algorithm / library for outcome prediction

  42. Actor-Critic in Discrete action spaces
  43. How to create domain rules from raw unstructured text using NLP and deep learning?

  44. Tensorflow regression predicting 1 for all inputs

  45. How to divide MNIST training dataset into subparts?

  46. Neural Networks overfitting

  47. What are default keras layer weights
  48. What network is called high-capacity network? Why?

  49. Text recognition within images
  50. How to feed the input to a Memory Augmented Neural Network (MAAN) to do one shot learning?
  51. Neural Networks with out normalization
  52. About LSTM cells, units and inputs
  53. What is the difference between Keras and Tflearn
  54. Advantages of monotonic activation functions over non-monotonic functions in neural networks?
  55. Multiple Output Layers in Neural Networks in Deep Q Learning
  56. Why should softmax be used in CNN
  57. speech accent recognition data augmentation and training

  58. AlexNet second layer understanding
  59. When to use GRU over LSTM?

  60. Why can it be that my neural network is predicting the contrary?

  61. Loss does not reduce on neural network for Cifar 10 dataset
  62. Predicting future airfare using past data
  63. How does neural network solve XOR problem

  64. Using a White noise image to minimise the loss in a (convolutional) neural network

  65. Keyword/phrase extraction from Text using Deep Learning libraries
  66. Why does it speed up gradient descent if the function is smooth?
  67. Data Augmentation for Regression
  68. How does timestep affects a stateless LSTM with batch_size=length(y) in keras?

  69. What is Compatible Function Approximation theorem in reinforcement learning?
  70. Isn't the optimizer network in deepminds learning to learn a DRQN?

  71. Can I use a regression machine learning model for predicting a vector with multiple values?

  72. Add a new category to pretrained model with N classifier, but all others will classify to this new category

  73. What is the difference between float64 and double in TensorFlow?

  74. the relationship between the number of filters/kernels and the number of feature maps
  75. Fine tuning accuracy lower than Raw Transfer Learning Accuracy
  76. What is training

  77. Deep Learning: Feed Forward for Unbalanced Classes Using Tensor Flow

  78. Crop background from Image
  79. Algorithms to get intent of an article?
  80. How to make output dimensions match input dimensions in CNN?

  81. The model of LSTM with more than one unit

  82. Pre-trained CNN for feature extraction
  83. Parameterization regression of rotation angle

  84. numpy.random.rand(m,n) produces matrix of 0 and -0

  85. How can I calculate Kernel matrix K for clustering based Kernel Principal Component Analysis?

  86. ML algorithms for defining NORMAL user behavior

  87. What is the efficient way to generate a similarity score when comparing two face images?

  88. Any pytorch tools to monitor neural network's training?
  89. Scientific explanation of Skip Connections
  90. Strange patterns from GAN

  91. How to update bias in CNN?

  92. How tangent distance works in three-dimentional space

  93. Implementing skill extraction using unsupervised approaches

  94. Do you know a dataset for regression where deep learning outperforms svm and random forests?

  95. How can we scale up the number of classes for deep learning after training a model?
  96. Keras or TensorFlow Examples for Working with Large Text Datasets (~10M Sentences)
  97. Are there libraries or techniques for 'noisifying' text data?

  98. Match an image from a set of images : Combine traditional Computer vision + Deep Learning/CNN

  99. How can we use InceptionV3 to recognize multiple object in 1 image (other then detection methods)

  100. What is the difference between observation and variable?