Architecture of a traditional CNN Convolutional neural networks, also known as CNNs, are a specific type of neural networks that are generally composed of the following layers: The convolution layer and the pooling layer can be fine-tuned with respect to hyperparameters that are described in. By Afshine Amidi and Shervine Amidi Overview. Architecture of a traditional RNN Recurrent neural networks, also known as RNNs, are a class of neural networks that allow previous outputs to be used as inputs while having hidden states.
By Afshine Amidi and Shervine Amidi
Overview
Architecture of a traditional CNN Convolutional neural networks, also known as CNNs, are a specific type of neural networks that are generally composed of the following layers:
The convolution layer and the pooling layer can be fine-tuned with respect to hyperparameters that are described in the next sections.
Types of layer
Convolution layer (CONV) The convolution layer (CONV) uses filters that perform convolution operations as it is scanning the input $I$ with respect to its dimensions. Its hyperparameters include the filter size $F$ and stride $S$. The resulting output $O$ is called feature map or activation map.
Remark: the convolution step can be generalized to the 1D and 3D cases as well.
Pooling (POOL) The pooling layer (POOL) is a downsampling operation, typically applied after a convolution layer, which does some spatial invariance. In particular, max and average pooling are special kinds of pooling where the maximum and average value is taken, respectively.
Type | Max pooling | Average pooling |
Purpose | Each pooling operation selects the maximum value of the current view | Each pooling operation averages the values of the current view |
Illustration | ||
Comments | • Preserves detected features • Most commonly used | • Downsamples feature map • Used in LeNet |
Fully Connected (FC) The fully connected layer (FC) operates on a flattened input where each input is connected to all neurons. If present, FC layers are usually found towards the end of CNN architectures and can be used to optimize objectives such as class scores.
Filter hyperparameters
The convolution layer contains filters for which it is important to know the meaning behind its hyperparameters.
Dimensions of a filter A filter of size $Ftimes F$ applied to an input containing $C$ channels is a $F times F times C$ volume that performs convolutions on an input of size $I times I times C$ and produces an output feature map (also called activation map) of size $O times O times 1$.
Remark: the application of $K$ filters of size $Ftimes F$ results in an output feature map of size $O times O times K$.
Stride For a convolutional or a pooling operation, the stride $S$ denotes the number of pixels by which the window moves after each operation.
Zero-padding Zero-padding denotes the process of adding $P$ zeroes to each side of the boundaries of the input. This value can either be manually specified or automatically set through one of the three modes detailed below:
Mode | Valid | Same | Full |
Value | $P = 0$ | $P_text{start} = Bigllfloorfrac{S lceilfrac{I}{S}rceil - I + F - S}{2}Bigrrfloor$ $P_text{end} = Bigllceilfrac{S lceilfrac{I}{S}rceil - I + F - S}{2}Bigrrceil$ | $P_text{start}in[![0,F-1]!]$ $P_text{end} = F-1$ |
Illustration | |||
Purpose | • No padding • Drops last convolution if dimensions do not match | • Padding such that feature map size has size $Bigllceilfrac{I}{S}Bigrrceil$ • Output size is mathematically convenient • Also called 'half' padding | • Maximum padding such that end convolutions are applied on the limits of the input • Filter 'sees' the input end-to-end |
Tuning hyperparameters
Parameter compatibility in convolution layer By noting $I$ the length of the input volume size, $F$ the length of the filter, $P$ the amount of zero padding, $S$ the stride, then the output size $O$ of the feature map along that dimension is given by:
Remark: often times, $P_text{start} = P_text{end} triangleq P$, in which case we can replace $P_text{start} + P_text{end}$ by $2P$ in the formula above.
Understanding the complexity of the model In order to assess the complexity of a model, it is often useful to determine the number of parameters that its architecture will have. In a given layer of a convolutional neural network, it is done as follows:
CONV | POOL | FC | |
Illustration | |||
Input size | $I times I times C$ | $I times I times C$ | $N_{text{in}}$ |
Output size | $O times O times K$ | $O times O times C$ | $N_{text{out}}$ |
Number of parameters | $(F times F times C + 1) cdot K$ | $0$ | $(N_{text{in}} + 1 ) times N_{text{out}}$ |
Remarks | • One bias parameter per filter • In most cases, $S < F$ • A common choice for $K$ is $2C$ | • Pooling operation done channel-wise • In most cases, $S = F$ | • Input is flattened • One bias parameter per neuron • The number of FC neurons is free of structural constraints |
Receptive field The receptive field at layer $k$ is the area denoted $R_k times R_k$ of the input that each pixel of the $k$-th activation map can 'see'.By calling $F_j$ the filter size of layer $j$ and $S_i$ the stride value of layer $i$ and with the convention $S_0 = 1$, the receptive field at layer $k$ can be computed with the formula:
In the example below, we have $F_1 = F_2 = 3$ and $S_1 = S_2 = 1$, which gives $R_2 = 1 + 2cdot 1 + 2cdot 1 = 5$.
Commonly used activation functions
Rectified Linear Unit The rectified linear unit layer (ReLU) is an activation function $g$ that is used on all elements of the volume. It aims at introducing non-linearities to the network. Its variants are summarized in the table below:
ReLU | Leaky ReLU | ELU |
$g(z)=max(0,z)$ | $g(z)=max(epsilon z,z)$ with $epsilonll1$ | $g(z)=max(alpha(e^z-1),z)$ with $alphall1$ |
• Non-linearity complexities biologically interpretable | • Addresses dying ReLU issue for negative values | • Differentiable everywhere |
Softmax The softmax step can be seen as a generalized logistic function that takes as input a vector of scores $xinmathbb{R}^n$ and outputs a vector of output probability $pinmathbb{R}^n$ through a softmax function at the end of the architecture. It is defined as follows:
Object detection
Types of models There are 3 main types of object recognition algorithms, for which the nature of what is predicted is different. They are described in the table below:
Image classification | Classification w. localization | Detection |
• Classifies a picture • Predicts probability of object | • Detects an object in a picture • Predicts probability of object and where it is located | • Detects up to several objects in a picture • Predicts probabilities of objects and where they are located |
Traditional CNN | Simplified YOLO, R-CNN | YOLO, R-CNN |
Detection In the context of object detection, different methods are used depending on whether we just want to locate the object or detect a more complex shape in the image. The two main ones are summed up in the table below:
Bounding box detection | Landmark detection |
• Detects the part of the image where the object is located | • Detects a shape or characteristics of an object (e.g. eyes) • More granular |
Box of center $(b_x,b_y)$, height $b_h$ and width $b_w$ | Reference points $(l_{1x},l_{1y}),$ $...,$ $(l_{nx},l_{ny})$ |
Intersection over Union Intersection over Union, also known as $textrm{IoU}$, is a function that quantifies how correctly positioned a predicted bounding box $B_p$ is over the actual bounding box $B_a$. It is defined as:
Remark: we always have $textrm{IoU}in[0,1]$. By convention, a predicted bounding box $B_p$ is considered as being reasonably good if $textrm{IoU}(B_p,B_a)geqslant0.5$.
Anchor boxes Anchor boxing is a technique used to predict overlapping bounding boxes. In practice, the network is allowed to predict more than one box simultaneously, where each box prediction is constrained to have a given set of geometrical properties. For instance, the first prediction can potentially be a rectangular box of a given form, while the second will be another rectangular box of a different geometrical form.
Non-max suppression The non-max suppression technique aims at removing duplicate overlapping bounding boxes of a same object by selecting the most representative ones. After having removed all boxes having a probability prediction lower than 0.6, the following steps are repeated while there are boxes remaining:
For a given class,
• Step 1: Pick the box with the largest prediction probability.
• Step 2: Discard any box having an $textrm{IoU}geqslant0.5$ with the previous box.
YOLO You Only Look Once (YOLO) is an object detection algorithm that performs the following steps:
• Step 1: Divide the input image into a $Gtimes G$ grid.
• Step 2: For each grid cell, run a CNN that predicts $y$ of the following form:
• Step 3: Run the non-max suppression algorithm to remove any potential duplicate overlapping bounding boxes.
Remark: when $p_c=0$, then the network does not detect any object. In that case, the corresponding predictions $b_x, ..., c_p$ have to be ignored.
R-CNN Region with Convolutional Neural Networks (R-CNN) is an object detection algorithm that first segments the image to find potential relevant bounding boxes and then run the detection algorithm to find most probable objects in those bounding boxes.
Remark: although the original algorithm is computationally expensive and slow, newer architectures enabled the algorithm to run faster, such as Fast R-CNN and Faster R-CNN.
Face verification and recognition
Types of models Two main types of model are summed up in table below:
Face verification | Face recognition |
• Is this the correct person? • One-to-one lookup | • Is this one of the $K$ persons in the database? • One-to-many lookup |
One Shot Learning One Shot Learning is a face verification algorithm that uses a limited training set to learn a similarity function that quantifies how different two given images are. The similarity function applied to two images is often noted $d(textrm{image 1}, textrm{image 2}).$
Siamese Network Siamese Networks aim at learning how to encode images to then quantify how different two images are. For a given input image $x^{(i)}$, the encoded output is often noted as $f(x^{(i)})$.
Triplet loss The triplet loss $ell$ is a loss function computed on the embedding representation of a triplet of images $A$ (anchor), $P$ (positive) and $N$ (negative). The anchor and the positive example belong to a same class, while the negative example to another one. By calling $alphainmathbb{R}^+$ the margin parameter, this loss is defined as follows:
Neural style transfer
Motivation The goal of neural style transfer is to generate an image $G$ based on a given content $C$ and a given style $S$.
Activation In a given layer $l$, the activation is noted $a^{[l]}$ and is of dimensions $n_Htimes n_wtimes n_c$
Content cost function The content cost function $J_{textrm{content}}(C,G)$ is used to determine how the generated image $G$ differs from the original content image $C$. It is defined as follows:
Style matrix The style matrix $G^{[l]}$ of a given layer $l$ is a Gram matrix where each of its elements $G_{kk'}^{[l]}$ quantifies how correlated the channels $k$ and $k'$ are. It is defined with respect to activations $a^{[l]}$ as follows:
Remark: the style matrix for the style image and the generated image are noted $G^{[l](S)}$ and $G^{[l](G)}$ respectively.
Style cost function The style cost function $J_{textrm{style}}(S,G)$ is used to determine how the generated image $G$ differs from the style $S$. It is defined as follows:
Overall cost function The overall cost function is defined as being a combination of the content and style cost functions, weighted by parameters $alpha,beta$, as follows:
Remark: a higher value of $alpha$ will make the model care more about the content while a higher value of $beta$ will make it care more about the style.
Architectures using computational tricks
Generative Adversarial Network Generative adversarial networks, also known as GANs, are composed of a generative and a discriminative model, where the generative model aims at generating the most truthful output that will be fed into the discriminative which aims at differentiating the generated and true image.
Remark: use cases using variants of GANs include text to image, music generation and synthesis.
ResNet The Residual Network architecture (also called ResNet) uses residual blocks with a high number of layers meant to decrease the training error. The residual block has the following characterizing equation:
Inception Network This architecture uses inception modules and aims at giving a try at different convolutions in order to increase its performance through features diversification. In particular, it uses the $1times1$ convolution trick to limit the computational burden.
Contents
- Cheat sheet
Algorithms
Deep Learning
Optimizers
neupy.algorithms.Momentum | Momentum algorithm. |
neupy.algorithms.GradientDescent | Mini-batch Gradient Descent algorithm. |
neupy.algorithms.Adam | Adam algorithm. |
neupy.algorithms.Adamax | AdaMax algorithm. |
neupy.algorithms.RMSProp | RMSProp algorithm. |
neupy.algorithms.Adadelta | Adadelta algorithm. |
neupy.algorithms.Adagrad | Adagrad algorithm. |
neupy.algorithms.ConjugateGradient | Conjugate Gradient algorithm. |
neupy.algorithms.QuasiNewton | Quasi-Newton algorithm. |
neupy.algorithms.LevenbergMarquardt | Levenberg-Marquardt algorithm is a variation of the Newton’s method. |
neupy.algorithms.Hessian | Hessian gradient decent optimization, also known as Newton’s method. |
neupy.algorithms.HessianDiagonal | Algorithm that uses calculates only diagonal values from the Hessian matrix and uses it instead of the Hessian matrix. |
neupy.algorithms.RPROP | Resilient backpropagation (RPROP) is an optimization algorithm for supervised learning. |
neupy.algorithms.IRPROPPlus | iRPROP+ is an optimization algorithm for supervised learning. |
Regularizers
neupy.algorithms.l1 | Applies l1 regularization to the trainable parameters in the network. |
neupy.algorithms.l2 | Applies l2 regularization to the trainable parameters in the network. |
neupy.algorithms.maxnorm | Applies max-norm regularization to the trainable parameters in the network. |
Recurrent Neural Network Cheat Sheet
Learning rate update rules
neupy.algorithms.step_decay | Algorithm minimizes learning step monotonically after each iteration. |
neupy.algorithms.exponential_decay | Applies exponential decay to the learning rate. |
neupy.algorithms.polynomial_decay | Applies polynomial decay to the learning rate. |
Neural Networks with Radial Basis Functions (RBFN)
neupy.algorithms.GRNN | Generalized Regression Neural Network (GRNN). |
neupy.algorithms.PNN | Probabilistic Neural Network (PNN). |
Autoasociative Memory
neupy.algorithms.DiscreteBAM | Discrete BAM Network with associations. |
neupy.algorithms.CMAC | Cerebellar Model Articulation Controller (CMAC) Network based on memory. |
neupy.algorithms.DiscreteHopfieldNetwork | Discrete Hopfield Network. |
Competitive Networks
neupy.algorithms.ART1 | Adaptive Resonance Theory (ART1) Network for binary data clustering. |
neupy.algorithms.GrowingNeuralGas | Growing Neural Gas (GNG) algorithm. |
neupy.algorithms.SOFM | Self-Organizing Feature Map (SOFM or SOM). |
neupy.algorithms.LVQ | Learning Vector Quantization (LVQ) algorithm. |
neupy.algorithms.LVQ2 | Learning Vector Quantization 2 (LVQ2) algorithm. |
neupy.algorithms.LVQ21 | Learning Vector Quantization 2.1 (LVQ2.1) algorithm. |
neupy.algorithms.LVQ3 | Learning Vector Quantization 3 (LVQ3) algorithm. |
Associative
neupy.algorithms.Oja | Oja is an unsupervised technique used for the dimensionality reduction tasks. |
neupy.algorithms.Kohonen | Kohonen Neural Network used for unsupervised learning. |
neupy.algorithms.Instar | Instar is a simple unsupervised Neural Network algorithm which detects associations. |
neupy.algorithms.HebbRule | Neural Network with Hebbian Learning. |
Boltzmann Machine
neupy.algorithms.RBM | Boolean/Bernoulli Restricted Boltzmann Machine (RBM). |
Layers
Layers with activation function
neupy.layers.Linear | Layer with linear activation function. |
neupy.layers.Sigmoid | Layer with the sigmoid used as an activation function. |
neupy.layers.HardSigmoid | Layer with the hard sigmoid used as an activation function. |
neupy.layers.Tanh | Layer with the hyperbolic tangent used as an activation function. |
neupy.layers.Relu | Layer with the rectifier (ReLu) used as an activation function. |
neupy.layers.LeakyRelu | Layer with the leaky rectifier (Leaky ReLu) used as an activation function. |
neupy.layers.Elu | Layer with the exponential linear unit (ELU) used as an activation function. |
neupy.layers.PRelu | Layer with the parametrized ReLu used as an activation function. |
neupy.layers.Softplus | Layer with the softplus used as an activation function. |
neupy.layers.Softmax | Layer with the softmax activation function. |
Neural Network Cheat Sheets
Convolutional layers
neupy.layers.Convolution | Convolutional layer. |
neupy.layers.Deconvolution | Deconvolution layer (also known as Transposed Convolution.). |
Recurrent layers
neupy.layers.LSTM | Long Short Term Memory (LSTM) Layer. |
neupy.layers.GRU | Gated Recurrent Unit (GRU) Layer. |
Pooling layers
neupy.layers.MaxPooling | Maximum pooling layer. |
neupy.layers.AveragePooling | Average pooling layer. |
neupy.layers.Upscale | Upscales input over two axis (height and width). |
neupy.layers.GlobalPooling | Global pooling layer. |
Normalization layers
neupy.layers.BatchNorm | Batch normalization layer. |
neupy.layers.GroupNorm | Group Normalization layer. |
neupy.layers.LocalResponseNorm | Local Response Normalization Layer. |
Stochastic layers
neupy.layers.Dropout | Dropout layer. |
neupy.layers.GaussianNoise | Add gaussian noise to the input value. |
neupy.layers.DropBlock | DropBlock, a form of structured dropout, where units in a contiguous region of a feature map are dropped together. |
Merge layers
neupy.layers.Elementwise | Layer merges multiple input with elementwise function and generate single output. |
neupy.layers.Concatenate | Concatenate multiple inputs into one. |
neupy.layers.GatedAverage | Layer uses applies weighted elementwise addition to multiple outputs. |
Other layers
neupy.layers.Input | Layer defines network’s input. |
neupy.layers.Identity | Passes input through the layer without changes. |
neupy.layers.Reshape | Layer reshapes input tensor. |
neupy.layers.Transpose | Layer transposes input tensor. |
neupy.layers.Embedding | Embedding layer accepts indices as an input and returns rows from the weight matrix associated with these indices. |
Operations
Additional operations that can be performed on the layers or graphs
neupy.layers.join(*networks) | Sequentially combines layers and networks into single network. |
neupy.layers.parallel(*networks) | Merges all networks/layers into single network without joining input and output layers together. |
neupy.layers.repeat(network_or_layer, n) | Function copies input n - 1 times and connects everything in sequential order. |
Architectures
neupy.architectures.vgg16 | VGG16 network architecture with random parameters. |
neupy.architectures.vgg19 | VGG19 network architecture with random parameters. |
neupy.architectures.squeezenet | SqueezeNet network architecture with random parameters. |
neupy.architectures.resnet50 | ResNet50 network architecture with random parameters. |
neupy.architectures.mixture_of_experts | Generates mixture of experts architecture from the set of networks that has the same input and output shapes. |
Parameter initialization
neupy.init.Constant | Initialize parameter that has constant values. |
neupy.init.Normal | Initialize parameter sampling from the normal distribution. |
neupy.init.Uniform | Initialize parameter sampling from the uniform distribution. |
neupy.init.Orthogonal | Initialize matrix with orthogonal basis. |
neupy.init.HeNormal | Kaiming He parameter initialization method based on the normal distribution. |
neupy.init.HeUniform | Kaiming He parameter initialization method based on the uniformal distribution. |
neupy.init.XavierNormal | Xavier Glorot parameter initialization method based on normal distribution. |
neupy.init.XavierUniform | Xavier Glorot parameter initialization method based on uniform distribution. |
Datasets
Neural Networks Pdf
neupy.datasets.load_digits | Returns dataset that contains discrete digits. |
neupy.datasets.make_digits | Returns discrete digits dataset. |
neupy.datasets.make_reber | Generate list of words valid by Reber grammar. |
neupy.datasets.make_reber_classification | Generate random dataset for Reber grammar classification. |