Recurrent Neural Networks

MIT Introduction to Deep Learning 6.S191: Lecture 2
New 2020 Edition
Recurrent Neural Networks
Lecturer: Ava Soleimany
January 2020

Lecture Outline
0:00 - Introduction
2:39 - Sequence modeling
9:57 - Recurrent neural networks
14:04 - RNN intuition
16:48 - Unfolding RNNs
20:31 - Backpropagation through time
24:32 - Gradient issues
28:57 - Long short term memory (LSTM)
37:36 - RNN applications
41:30 - Attention
44:05 - Summary

#machine-learning #data-science #deep-learning

What is GEEK

Buddha Community

Recurrent Neural Networks

A Comparative Analysis of Recurrent Neural Networks

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. RNN models are mostly used in the fields of natural language processing and speech recognition.

The vanishing and exploding gradient phenomena are often encountered in the context of RNNs. The reason why they happen is that it is difficult to capture long term dependencies because of multiplicative gradient that can be exponentially decreasing/increasing with respect to the number of layers.

Gated Recurrent Unit (GRU) and Long Short-Term Memory units (LSTM) deal with the vanishing gradient problem encountered by traditional RNNs, with LSTM being a generalization of GRU.

1D Convolution_ layer_ creates a convolution kernel that is convolved with the layer input over a single spatial (or temporal) dimension to produce a tensor of outputs. It is very effective for deriving features from a fixed-length segment of the overall dataset. A 1D CNN works well for natural language processing (NLP).

DATASET: IMDb Movie Review

TensorFlow Datasets is a collection of datasets ready to use, with TensorFlow or other Python ML frameworks, such as Jax. All datasets are exposed as [](, enabling easy-to-use and high-performance input pipelines.


This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. It provides a set of 25,000 highly polar movie reviews for training, and 25,000 for testing.

Import Libraries

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

Load the Dataset

import tensorflow as tf
import tensorflow_datasets

imdb, info=tensorflow_datasets.load("imdb_reviews", with_info=True, as_supervised=True)

Image for post


Image for post

Training and Testing Data

train_data, test_data=imdb['train'], imdb['test']

for s,l in train_data:
for s,l in test_data:

Tokenization and Padding

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
tokenizer= Tokenizer(num_words=vocab_size, oov_token=oov_tok)
padded=pad_sequences(sequences, maxlen=max_length, truncating=trunc_type)
testing_padded=pad_sequences(testing_sequences, maxlen=max_length)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Embedding

Multi-layer Bidirectional LSTM

#imdb #convolutional-network #long-short-term-memory #recurrent-neural-network #gated-recurrent-unit #neural networks

Marlon  Boyle

Marlon Boyle


Recurrent Neural Networks for Multilabel Text Classification Tasks

The purpose of this project is to build and evaluate Recurrent Neural Networks(RNNs) for sentence-level classification tasks. I evaluate three architectures: a two-layer Long Short-Term Memory Network(LSTM), a two-layer Bidirectional Long Short-Term Memory Network(BiLSTM), and a two-layer BiLSTM with a word-level attention layer. Although they do learn useful vector representation, BiLSTM with attention mechanism focuses on necessary tokens when learning text representation. To that end, I’m using the 2019 Google Jigsaw published dataset on Kaggle labeled “Jigsaw Unintended Bias in Toxicity Classification.” The dataset includes 1,804,874 user comments, with the toxicity level being between 0 and 1. The final models can be used for filtering online posts and comments, social media policing, and user education.


Recurrent Neural Networks Overview

RNNs are neural networks used for problems that require sequential data processing. For instance:

  • In a sentiment analysis task, a text’s sentiment can be inferred from a sequence of words or characters.
  • In a stock prediction task, current stock prices can be inferred from a sequence of past stock prices.

At each time step of the input sequence, RNNs compute the output yt and an internal state update ht using the input xt and the previous hidden-state ht-1. They then pass information about the current time step of the network to the next. The hidden-state ht summarizes the task-relevant aspect of the past sequence of the input up to t, allowing for information to persist over time.

Image for post

Recurrent Neural Network

Image for post

Recurrent Neural Network

During training, RNNs re-use the same weight matrices at each time step. Parameter sharing enables the network to generalize to different sequence lengths. The total loss is a sum of all losses at each time step, the gradients with respect to the weights are the sum of the gradients at each time step, and the parameters are updated to minimize the loss function.

Image for post

forward pass: compute the loss function

Image for post

Image for post

loss function

Image for post

Backward Pass: compute the gradients

Image for post

gradient equation

Although RNNs learn contextual representations of sequential data, they suffer from the exploding and vanishing gradient phenomena in long sequences. These problems occur due to the multiplicative gradient that can exponentially increase or decrease through time. RNNs commonly use three activation functions: RELU, Tanh, and Sigmoid. Because the gradient calculation also involves the gradient with respect to the non-linear activations, architectures that use a RELU activation can suffer from the exploding gradient problem. Architectures that use Tanh/Sigmoid can suffer from the vanishing gradient problem. Gradient clipping — limiting the gradient within a specific range — can be used to remedy the exploding gradient. However, for the vanishing gradient problem, a more complex recurrent unit with gates such as Gated Recurrent Unit (GRU) or Long Short-Term Memory (LSTM) can be used.

#ai #recurrent-neural-network #attention-network #machine-learning #neural-network

The Recurrent Neural Network (RNNs)

A recurrent neural network (RNN) is an input node (hidden layer) that feeds sigmoid activation. The way an RNN does this is to take the output of one neuron and return it as input to another neuron or feed the input of the current time step to the output of earlier time steps. Here you feed the input from the previous times step by step into the input of the current times and vice versa.

Image for post

This can be used in a variety of ways, such as through learning gates with known variations or a combination of sigmoid activation and a number of other types of neural networks.

Some of the applications for RNNs include predicting energy demand, predicting stock prices, and predicting human behavior. RNNs are modeled over time — based and sequence-based data, but they are also useful in a variety of other applications.

A recurrent neural network is an artificial neural network used for deep learning, machine learning, and other forms of artificial intelligence (AI). They have a number of attributes that make them useful for tasks where data needs to be processed sequentially.

To get a little more technical, recurring neural networks are designed to learn a sequence of data by traversing a hidden state from one step of the sequence to the next, combined with the input, and routing it back and forth between the inputs. RNN are neural networks that are designed for the effective handling of sequential data but are also useful for non-sequential data.

These types of data include text documents that can be seen as a sequence of words or audio files in which you can see a sequence of sound frequencies and times. The more information about the output layer is available, the faster it can be read and sequenced, and the better its performance.

#recurrent-neural-network #lstm #rnn #artificial-intelligence #neural network

Mckenzie  Osiki

Mckenzie Osiki


No Code introduction to Neural Networks

The simple architecture explained

Neural networks have been around for a long time, being developed in the 1960s as a way to simulate neural activity for the development of artificial intelligence systems. However, since then they have developed into a useful analytical tool often used in replace of, or in conjunction with, standard statistical models such as regression or classification as they can be used to predict or more a specific output. The main difference, and advantage, in this regard is that neural networks make no initial assumptions as to the form of the relationship or distribution that underlies the data, meaning they can be more flexible and capture non-standard and non-linear relationships between input and output variables, making them incredibly valuable in todays data rich environment.

In this sense, their use has took over the past decade or so, with the fall in costs and increase in ability of general computing power, the rise of large datasets allowing these models to be trained, and the development of frameworks such as TensforFlow and Keras that have allowed people with sufficient hardware (in some cases this is no longer even an requirement through cloud computing), the correct data and an understanding of a given coding language to implement them. This article therefore seeks to be provide a no code introduction to their architecture and how they work so that their implementation and benefits can be better understood.

Firstly, the way these models work is that there is an input layer, one or more hidden layers and an output layer, each of which are connected by layers of synaptic weights¹. The input layer (X) is used to take in scaled values of the input, usually within a standardised range of 0–1. The hidden layers (Z) are then used to define the relationship between the input and output using weights and activation functions. The output layer (Y) then transforms the results from the hidden layers into the predicted values, often also scaled to be within 0–1. The synaptic weights (W) connecting these layers are used in model training to determine the weights assigned to each input and prediction in order to get the best model fit. Visually, this is represented as:

#machine-learning #python #neural-networks #tensorflow #neural-network-algorithm #no code introduction to neural networks

Marlon  Boyle

Marlon Boyle


Autonomous Driving Network (ADN) On Its Way

Talking about inspiration in the networking industry, nothing more than Autonomous Driving Network (ADN). You may hear about this and wondering what this is about, and does it have anything to do with autonomous driving vehicles? Your guess is right; the ADN concept is derived from or inspired by the rapid development of the autonomous driving car in recent years.

Image for post

Driverless Car of the Future, the advertisement for “America’s Electric Light and Power Companies,” Saturday Evening Post, the 1950s.

The vision of autonomous driving has been around for more than 70 years. But engineers continuously make attempts to achieve the idea without too much success. The concept stayed as a fiction for a long time. In 2004, the US Defense Advanced Research Projects Administration (DARPA) organized the Grand Challenge for autonomous vehicles for teams to compete for the grand prize of $1 million. I remembered watching TV and saw those competing vehicles, behaved like driven by drunk man, had a really tough time to drive by itself. I thought that autonomous driving vision would still have a long way to go. To my surprise, the next year, 2005, Stanford University’s vehicles autonomously drove 131 miles in California’s Mojave desert without a scratch and took the $1 million Grand Challenge prize. How was that possible? Later I learned that the secret ingredient to make this possible was using the latest ML (Machine Learning) enabled AI (Artificial Intelligent ) technology.

Since then, AI technologies advanced rapidly and been implemented in all verticals. Around the 2016 time frame, the concept of Autonomous Driving Network started to emerge by combining AI and network to achieve network operational autonomy. The automation concept is nothing new in the networking industry; network operations are continually being automated here and there. But this time, ADN is beyond automating mundane tasks; it reaches a whole new level. With the help of AI technologies and other critical ingredients advancement like SDN (Software Defined Network), autonomous networking has a great chance from a vision to future reality.

In this article, we will examine some critical components of the ADN, current landscape, and factors that are important for ADN to be a success.

The Vision

At the current stage, there are different terminologies to describe ADN vision by various organizations.
Image for post

Even though slightly different terminologies, the industry is moving towards some common terms and consensus called autonomous networks, e.g. TMF, ETSI, ITU-T, GSMA. The core vision includes business and network aspects. The autonomous network delivers the “hyper-loop” from business requirements all the way to network and device layers.

On the network layer, it contains the below critical aspects:

  • Intent-Driven: Understand the operator’s business intent and automatically translate it into necessary network operations. The operation can be a one-time operation like disconnect a connection service or continuous operations like maintaining a specified SLA (Service Level Agreement) at the all-time.
  • **Self-Discover: **Automatically discover hardware/software changes in the network and populate the changes to the necessary subsystems to maintain always-sync state.
  • **Self-Config/Self-Organize: **Whenever network changes happen, automatically configure corresponding hardware/software parameters such that the network is at the pre-defined target states.
  • **Self-Monitor: **Constantly monitor networks/services operation states and health conditions automatically.
  • Auto-Detect: Detect network faults, abnormalities, and intrusions automatically.
  • **Self-Diagnose: **Automatically conduct an inference process to figure out the root causes of issues.
  • **Self-Healing: **Automatically take necessary actions to address issues and bring the networks/services back to the desired state.
  • **Self-Report: **Automatically communicate with its environment and exchange necessary information.
  • Automated common operational scenarios: Automatically perform operations like network planning, customer and service onboarding, network change management.

On top of those, these capabilities need to be across multiple services, multiple domains, and the entire lifecycle(TMF, 2019).

No doubt, this is the most ambitious goal that the networking industry has ever aimed at. It has been described as the “end-state” and“ultimate goal” of networking evolution. This is not just a vision on PPT, the networking industry already on the move toward the goal.

David Wang, Huawei’s Executive Director of the Board and President of Products & Solutions, said in his 2018 Ultra-Broadband Forum(UBBF) keynote speech. (David W. 2018):

“In a fully connected and intelligent era, autonomous driving is becoming a reality. Industries like automotive, aerospace, and manufacturing are modernizing and renewing themselves by introducing autonomous technologies. However, the telecom sector is facing a major structural problem: Networks are growing year by year, but OPEX is growing faster than revenue. What’s more, it takes 100 times more effort for telecom operators to maintain their networks than OTT players. Therefore, it’s imperative that telecom operators build autonomous driving networks.”

Juniper CEO Rami Rahim said in his keynote at the company’s virtual AI event: (CRN, 2020)

“The goal now is a self-driving network. The call to action is to embrace the change. We can all benefit from putting more time into higher-layer activities, like keeping distributors out of the business. The future, I truly believe, is about getting the network out of the way. It is time for the infrastructure to take a back seat to the self-driving network.”

Is This Vision Achievable?

If you asked me this question 15 years ago, my answer would be “no chance” as I could not imagine an autonomous driving vehicle was possible then. But now, the vision is not far-fetch anymore not only because of ML/AI technology rapid advancement but other key building blocks are made significant progress, just name a few key building blocks:

  • software-defined networking (SDN) control
  • industry-standard models and open APIs
  • Real-time analytics/telemetry
  • big data processing
  • cross-domain orchestration
  • programmable infrastructure
  • cloud-native virtualized network functions (VNF)
  • DevOps agile development process
  • everything-as-service design paradigm
  • intelligent process automation
  • edge computing
  • cloud infrastructure
  • programing paradigm suitable for building an autonomous system . i.e., teleo-reactive programs, which is a set of reactive rules that continuously sense the environment and trigger actions whose continuous execution eventually leads the system to satisfy a goal. (Nils Nilsson, 1996)
  • open-source solutions

#network-automation #autonomous-network #ai-in-network #self-driving-network #neural-networks