Deep Learning questions and answers
Neural network architectures, training dynamics and GPU execution. Page 1 of 20.
ML System Design practice on Codemia
Design recommenders, ranking systems and training pipelines the way ML interviews actually ask for them, with worked solutions.
Answers 1-60
- 4D input in LSTM layer in Keras
- About tensorflow Metadata and RunOptions
- About tensorflow.initialize_all_variables
- Accessing PyTorch GPU matrix from TensorFlow directly
- Accuracy issue in caffe
- Adam optimizer goes haywire after 200k batches, training loss grows
- Adam optimizer with warmup on PyTorch
- Add L2 regularization when using high level tf.layers
- Adding a preprocessing layer to keras model and setting tensor values
- Adding a variable into Keras/TensorFlow CNN dense layer
- Adding a variable into Keras/TensorFlow CNN dense layer
- Adding an additional value to a Convolutional Neural Network Input?
- Adding an extra hidden layer using Google's TensorFlow
- Adding Attention on top of simple LSTM layer in Tensorflow 2.0
- Adding multiple layers to TensorFlow causes loss function to become Nan
- Adding regularizer to an existing layer of a trained model without resetting weights?
- Adjust Single Value within Tensor -- TensorFlow
- After building TensorFlow from source, seeing libcudart.so and libcudnn errors
- AlexNet architecture for black and white image identification
- Anaconda Integration with Cuda 9.0 shows Incompatible Package Error
- Analysis of the output from tf.nn.dynamic_rnn tensorflow function
- API Reference for `RNN` and Seq2Seq models in tensorflow
- Apply function for every pair of elements in two Tensors in Tensorflow
- Applying callbacks in a custom training loop in Tensorflow 2.0
- Appropriate Deep Learning Structure for multi-class classification
- Appropriate Deep Learning Structure for multi-class classification
- Arbitrary dataset in cat detecting deep learning work of Google?
- Arbitrary filters for conv2d as opposed to rectangular
- Are modern CNN convolutional neural network as DetectNet rotate invariant?
- Are there any examples of anomaly detection algorithms implemented with TensorFlow?
- Are there pre-trained LSTM, RNN, or ANN models for time-series prediction?
- Arguments to tensorflow session.run - do you pass operations?
- Asynchronous computation in TensorFlow
- Attempting to reset tensorflow graph when using keras, failing
- AttributeError module 'keras.utils' has no attribute 'Sequence
- AttributeError module 'tensorflow' has no attribute 'name_scope' with Keras
- Auto-encoders with tied weights in Caffe
- Average layer in multi input deep learning
- Average weights in keras models
- AWS SageMaker on GPU
- Backpropagation algorithm through cross-channel local response normalization LRN layer
- Backpropagation in Convolutional Neural Networks
- Backpropagation in Pooling Layer Subsamplig layer in CNN
- Backpropagation with Momentum
- Basic 1d convolution in tensorflow
- Basic tensorflow classification example
- Batch normalization during testing
- Batch Normalization in Convolutional Neural Network
- Batch normalization instead of input normalization
- Batch normalization layer for CNN-LSTM
- Batch normalization when batch size1
- Batch normalization with 3D convolutions in TensorFlow
- Batch normalization with 3D convolutions in TensorFlow
- batch size in model.fit and model.predict
- Batch_size in tensorflow? Understanding the concept
- Batchnorm2d Pytorch - Why pass number of channels to batchnorm?
- Best practice for upgrading CUDA and cuDNN for tensorflow
- Best way to flatten a 2D tensor containing a vector in TensorFlow?
- Bidirectional LSTM output question in PyTorch
- Bilinear upsample in tensorflow?
.png&w=3840&q=75)
Free course
Beginner
7 lessons
2 hours
Tackling System Design Interview Problems
A short course that equips you with the skills to approach system design interviews methodically.
Start the free course