Assembling a perfect personal computer, that meets various varying requirements of a family such as gaming, regular usage, programming, etc., in such a huge market of features is quite a challenge nowadays.

Despite the efforts put by consumers to customize their computers to meet the different requirements, the percentage of satisfied consumers is very less. This session aims to propose and demonstrate a genetic algorithm approach to find the optimum set of features, given that each feature adds to the cost of the computer but provides some benefit to the consumer, the selected features must be fulfilled within a given budget. The experimental result yields the average fitness convergence at value 5524 which is a marked improvement over 23% over a recently published paper that used the Group Selection Technique along with single-point crossover for hardware selection.

 
 

Outline/Structure of the Demonstration

This session will discuss:-

  • Introduction to Genetic Algorithms (GA) (3 Mins)
  • The analogy with Biological systems (2 Mins)
  • Various Operations possible in GA ( including encoding, crossover, mutation and Fitness Function) (4 Min)
  • Different Use Cases (3 Min)
  • Proposed Algorithm and Live Hands-on code for solving Computer Assembling Problem with results. (7 Min)
  • Questions and Answers

Learning Outcome

By attending the session, the attendee would learn about basic and advanced techniques applied in genetic algorithms in various scenarios, including how to use them in solving real-world problems.

Target Audience

Data Scientists, Data Engineers, Data Specialists, Machine Learning Engineers, Artificial Intelligence Enthusiasts, Everyone who faces dilemma while buying a new Computer.

Prerequisites for Attendees

None

schedule Submitted 3 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Kuldeep Jiwani
    By Kuldeep Jiwani  ~  2 months ago
    reply Reply

    Hi Vrishank & Saakshi,

    Can you provide the link to the paper that you claim you have gained improvement upon.

    "The experimental result yields the average fitness convergence at value 5524 which is a marked improvement over 23% over a recently published paper that used the Group Selection Technique along with single-point crossover for hardware selection."

    • Vrishank Gupta
      By Vrishank Gupta  ~  2 months ago
      reply Reply

      Hi Kuldeep,

      Thanks for your interest in our proposal.

      Here is the link to the above-mentioned paper.

       

      Regards

      Vrishank Gupta

  • Ashay Tamhane
    By Ashay Tamhane  ~  2 months ago
    reply Reply

    Thanks for the proposal. Just trying to understand the importance of this problem better. Could you please provide some reference or numbers on this claim: "Despite the efforts put by consumers to customize their computers to meet the different requirements, the percentage of satisfied consumers is very less."

    • Vrishank Gupta
      By Vrishank Gupta  ~  2 months ago
      reply Reply

      Sir,

      As per findings by ACSI (American Customer Satisfaction Index) ( which feeds survey data as input to ACSI’s proprietary model and embeds customer satisfaction within a series of cause-and-effect relationships), the number of satisfied personal computer consumers has been declining over the past few years in comparison to users of other alternatives to personal computers such as tablets, etc.. A few articles have also been published such as this and this. This talk aims at suggesting various optimal sets of features that might help in enhancing user experience and hence increase the satisfaction levels. 

       

      Moreover, this talk aims at demonstrating how Genetic Algorithms can be applied to not only this problem but also to more general world problems and obtain exceptional results by showing a live hands-on demo on solving the above-said problem through a code. It also aims to build the aptitude that how a general problem can be encoded in computational space and therefore, solved by feeding to metaheuristics such as the Genetic Algorithm.

       

      Regards

      Vrishank Gupta

  • navjot bansal
    By navjot bansal  ~  3 months ago
    reply Reply

    hi vrishank great submission i was flabbergasted by the word you guys have done 

  • Santonu Goswami
    By Santonu Goswami  ~  3 months ago
    reply Reply

    Hi Vrishank and Saakshi, 

    Thank you for your interesting submission. 

    I need little help in understanding the proposal little better. While your proposal seems to talk about a possible use case of implementing a genetic algorithm to solve the problem of Assembling a Perfect Personal Computer, your talk outline assigns just 2 mins to talk about Algorithms and Insights. Could you please clarify if you have implemented any algorithm yourselves to the specific problem?

    Thanks, 

    Santonu

    • Vrishank Gupta
      By Vrishank Gupta  ~  3 months ago
      reply Reply

      Respected sir,

      Thanks for showing interest in our proposal.

      Yes, we have implemented a Genetic Algorithm to solve computer assembling problem and are going to present it during the talk.

      Our whole talk aims at building concepts to finally present the code and interesting results that we achieved in solving the computer assembling problem using genetic algorithms.

      Upon your suggestion, we have updated the intended outline and time-wise breakup of our presentation for better clarity.

       

      Regards

      Vrishank

  • Natasha Rodrigues
    By Natasha Rodrigues  ~  3 months ago
    reply Reply

    Hi Vrishank,

    Thanks for your proposal! Requesting you to update the Outline/Structure section of your proposal with a time-wise breakup of how you plan to use 20 mins for the topics you've highlighted?

    Thank you for your Saakshi's video, however to help the program committee understand your presentation style as well, can you provide a link to your past recording or record a small 1-2 mins trailer of your talk and share the link to the same?

    Thanks,

    Natasha

    • Vrishank Gupta
      By Vrishank Gupta  ~  3 months ago
      reply Reply

      Hello Natasha, thanks for your suggestions.

       

      As for the video presentation, would something like the following video work? With screen sharing and person live view presenting live to the audience? YouTube Video Link

       

      PS. It's not my video, just asking for clarity

      • Natasha Rodrigues
        By Natasha Rodrigues  ~  3 months ago
        reply Reply

        Hi Vrishank,

        Having you the presenter in the video would work for us, even if its 1-2 mins clip.

        Thanks,

        Natasha 

        • Vrishank Gupta
          By Vrishank Gupta  ~  3 months ago
          reply Reply

          Hi Natasha,

          I've updated the video inside the section "Links" with the link name GA_Vrishank, it links to the video with me giving the presentation.

           

          Hope that meets the requirements.

           

          Regards

          Vrishank Gupta

  • Simar Singh
    By Simar Singh  ~  3 months ago
    reply Reply

    Kudos man, you've hit the spot accurately, we all do face this dilemma. Looking forward to attend this session


  • Liked Saakshi Bhargava
    keyboard_arrow_down

    Saakshi Bhargava / Vrishank Gupta - Generative Adversarial Networks (GANs)

    20 Mins
    Demonstration
    Beginner

    Deep learning has accomplished pronounced triumph in the field of artificial intelligence, there are many deep learning models that have been developed in the recent time. Generative Models (GAN) are one of the deep learning models, that was given based on the game theory called zero-sum and now has been treated as the hot area for research. Generative Models are modern techniques used in computer vision. Unlike other neural networks that are used for predictions from images, generative models can generate new images as well for specific objectives. They can be used for generating huge datasets. This session will review several applications of generative modeling such as image generation and image translation, video frame prediction using CNNs and GANs.

  • Liked Abdul Azeez
    keyboard_arrow_down

    Abdul Azeez - Photo-Realistic Single Image Super-Resolution using SRGAN

    Abdul Azeez
    Abdul Azeez
    Data Scientist
    Nexquare
    schedule 3 months ago
    Sold Out!
    20 Mins
    Demonstration
    Advanced

    As we know, a basic GAN has two neural Networks – the Discriminator (D) and the Generator (G). The Generator attempts to generate images that look like real images. The Discriminator tries to distinguish the generated images from real images. By combined loss minimization of these two neural networks, the entire model trains and eventually reach a state of equilibrium, where the Discriminator no longer can distinguish the fake images, generated by the Generator, from real images.


    In this talk, I'll be discussing how GANs can be used to achieve Super Resolution. Super Resolution is the process of upscaling and or improving the details within an image. Often a Low Resolution image is taken as an input and the same image is upscaled to a higher resolution, which is the output. The details in the High Resolution output are filled in where the details are essentially unknown.

    The traditional way of upscaling an image was to perform interpolation over the pixels such as Bicubic Interpolation. Drawbacks of this method are images that get smoothened or details and definitions are lost.

    The need for high resolution is extensive right from a portrait we capture from our phone to image recognition, forensic science, etc.

  • Liked Vivek Singhal
    keyboard_arrow_down

    Vivek Singhal - How to start and grow an AI Lab

    20 Mins
    Experience Report
    Beginner

    I will discuss how I started CellStrat AI Lab and what goes to make it successful as one of the leading AI research groups in India.

    I will cover facets such as origination, growth, researcher motivation, content portfolio, project activity, research areas, marketing techniques and talent development pipeline.

    This presentation will give an idea to corporate and academic institutions as to how they can create and nurture a world-class AI Lab within their organizations.

  • Liked Anupam Ranjan
    keyboard_arrow_down

    Anupam Ranjan / Yash Raj - SQUAD application through Knowledge Graph for COVID-19 Literature

    20 Mins
    Demonstration
    Advanced

    There are numerous documents and research papers being published for COVID-19 and doctors are not able to absorb the content of all the literature. It has become a real challenge to extract relevant information in a short span of time.

    Knowledge Graph along with SQUAD application can help process multiple documents and extract precise information from a set of documents quickly. This will be a very handy application for healthcare professional to extract relevant information without going in detail with each application.

    The session will demonstrate the following:

    a) Text Processing of COVID-19 literature

    b) Named Entity Extraction from the documents using BERT/Spacy

    c) Building a Knowledge Graph of the documents

    d) Building question-answer application

  • Liked Vishal Singhal
    keyboard_arrow_down

    Vishal Singhal - How to Fulfill Management’s Enterprise AI Initiative

    20 Mins
    Talk
    Executive

    Artificial Intelligence fulfillment is a hot topic these days across continents and boardrooms of all small to mid-range to large companies alike. A common question for everybody is to understand as to how they can utilise the technology, deploy it in their business and what will it take to achive this business objective. “How to Fulfill Management’s Enterprise AI Initiative” topic addresses most of such queries and attempts to answer them taking a well-rounded perspective in the Indian Enterprise context.

  • Liked Vivek Singhal
    keyboard_arrow_down

    Vivek Singhal / Niraj Kale - Scalable and Efficient Object Detection with EfficientDet

    20 Mins
    Talk
    Intermediate

    There has been much research in efficient and scalable model approaches required for network design and object detection. Feature Pyramid Networks (FPN) enabled feature fusion at different scales. Path Aggregation Networks (PANet) conduct bottom-up path augmentation in an FPN, which shortens information transfer from bottom layers to topmost features. A more recent scheme, NAS-FPN (Neural Architecture Search-Feature Pyramid Network), combines RL-based NAS with an FPN to enable combination of top-down and bottom-up connections to fuse features across scales.

    A recent state-of-the art model EfficientDet uses a weighted bi-directional BiFPN with multi-scale feature fusion across layers to account for learnable feature importance while applying bottom-up and top-down feature fusion. EfficientDet combines BiFPN with efficient model scaling techniques proposed in EfficientNet model, such that the baseline network, the feature network and the bounding box/class prediction networks are all scaled uniformly and efficiently using compound scaling technique across resolution/width/depth dimensions. The EfficientNet-D6 achieves top of the line accuracy (mAP) on COCO dataset with 4x lesser parameters and 13x fewer FLOPS then the recent comparable NAS-FPN model.

  • Liked Indrajit Singh
    keyboard_arrow_down

    Indrajit Singh - Modern QA System using BERT and DistilBERT

    Indrajit Singh
    Indrajit Singh
    AI Researcher
    CellStrat
    schedule 3 months ago
    Sold Out!
    20 Mins
    Experience Report
    Advanced

    A QA system finds the answers out of the help with the information retrieval, computational linguistics and knowledge representation of the data for finding those answers for the questions given. I have used the #google #BERT pretrained model for building a QA system. The QA system is extracting the data from Web/Database using IR and feeding the paragraph as input to the system which retrieves the answer based on the answer given as input to the system. BERT is one such pre-trained model developed by Google which can be fine-tuned on new data which can be used to create NLP systems like question answering, text generation, text classification, text summarization and sentiment analysis.

    In this talk, I will be discussing the end to end architecture of modern Question Answering Systems and how they are different from chat-bots using SQUAD 2.0. How QA Based systems can help modernize multiple industries such as pharmaceutical, Automobile and Retail etc,domains in solving various complex challenges. I will be discussing in detail about masked language models and sentence prediction and how that's helping BERT/DistilBERT to be top production-ready algorithms.

    We will see how various BERT variants like SciBERT and BioBERT are helping in focusing on a specific domain or area. A clear understanding of Token Embedding - Segmanet Embedding - Position Embedding as the primary base behind these algorithms.

  • 20 Mins
    Demonstration
    Intermediate

    Reinforcement Learning broadly involves Value-based methods and Policy-based Methods. Actor-based methods are suitable for discrete action spaces, whereas Policy-based methods are suitable for continuous action spaces.

    A simple Policy Gradient algorithm (a policy-based method) predicts the probability of Actions of an Agent. Since, the Policy is updated using Monte Carlo approach (i.e. taking random samples), the variance of log probabilities produced by the PG algorithm is very high, causing unstable learning. This variance can be reduced by using a Baseline to remove outliers. A good choice to be used as a baseline is the Q-Value of the State, Action pair.

    In this session, we will talk about Actor Critic algorithms, which uses two networks - an Actor and a Critic. The actor outputs the Policy, while the Critic gives out the Q-value which can be used to evaluate the Policy. In this zero-sum game, an equilibrium is reached when an ideal policy is discovered.

    We will demonstrate with a Code demo, how this algorithm can be used to predict Actions in a Stock market scenario.

  • Liked Shubha Manikarnike
    keyboard_arrow_down

    Shubha Manikarnike - Collaboration and Competition in Multi-Agent RL

    20 Mins
    Demonstration
    Intermediate

    In Deep Reinforcement Learning, we know that policy Gradient methods work efficiently in predicting the probability of the Actions, in case of discrete Action Spaces and the exact action itself incase of continous Actions. The Predicted Action is evaluated by another Neural Network. We have used this to train a Robotic Arm to perform specific Tasks.

    But what if we have more One Agent in an environment to be trained?.You can have an autonomous group of agents sharing a common environment. These Agents can work Collaboratively towards maximizing their total goal, or they could be interacting Competitively against each other to get the Reward, or they can be interacting in a mixed mode.

    In this session, I will talk about Multi Agent Reinforcement Algorithms (MARL) which can be used in either collaborative mode, or competitive mode or a mixed mode between Agents. I will present a brief Code walk through of using the above algorithm in Open AI's Multi Agent Particle Environment.

  • Liked Bhavesh Laddagiri
    keyboard_arrow_down

    Bhavesh Laddagiri - Getting closer to Artificial General Intelligence with Neuro-Symbolic AI

    Bhavesh Laddagiri
    Bhavesh Laddagiri
    AI Researcher
    CellStrat AI Lab
    schedule 3 months ago
    Sold Out!
    20 Mins
    Demonstration
    Advanced

    The recent advances in AI over the last decade has been heavily powered by Deep Learning with a new SOTA algorithm being released every other week by developers and researchers all across the globe. The concept of neural networks came into existence in the 1960s but made a come-back when fueled by the massive datasets and GPU farms. But the field of AI is much richer than just this one type of algorithm. Symbolic reasoning based algorithms also pioneered in the 1960s and were more practical for the time as they were less computationally intensive.

    Deep Learning is great at understanding and finding patterns in massive streams of data but fails when it comes to using logic and reasoning to understand a concept with minimal data. Symbolic AI, on the other hand, is good at reasoning and creating abstractions from pre-defined concepts but fails to scale to real-world problems. However, there is something interesting here, the weaknesses of neural nets are actually the strengths of symbolic AI (and vice-versa), for the most part. So why not, Hybridize AI with Neural Nets and Symbolic AI to pave out a path for human-level AGI?

    In this session, we are going to learn how this radical approach to AI can help solve real-world problems by demonstrating my proof-of-concept which can navigate a simple environment using natural language commands in a few shots of training. This demo will also allow the attendees to understand the usage of pretrained models for generalizing to new tasks using a multi-modal approach. Finally, we will look at the industry use cases of Neuro-Symbolic AI and the potential advantages of this approach over vanilla deep learning in that domain.

  • Liked Darshan Ganji
    keyboard_arrow_down

    Darshan Ganji / Deepesh Agrawal - On-Demand Accelerating Deep Neural Network Inference via Edge Computing

    20 Mins
    Demonstration
    Advanced

    Deep Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on mobile phones and embedded systems with limited hardware resources and taking more time for Inference and Training. For many mobile-first companies such as Baidu and Facebook, various apps are updated via different app stores, and they are very sensitive to the size of the binary files. For example, App Store has the restriction “apps above 100 MB will not download until you connect to Wi-Fi”. As a result, a feature that increases the binary size by 100MB will receive much more scrutiny than one that increases it by 10MB. It is challenging to run computation-intensive DNN-based tasks on mobile devices due to the limited computation resources.

    This talk introduces the Algorithms and Hardware that can be used to accelerate the Inferencing or reduce the latency of deep learning workloads. We will discuss how to compress the Deep Neural Networks and techniques like Graph Fusion, Kernel Auto-Tuning for accelerating inference, as well as Data and model parallelization, automatic mixed precision, and other techniques for accelerating training. We will also discuss specialized hardware for deep learning such as GPUs, FPGAs, and ASICs, including the Tensor Cores in NVIDIA’s Volta GPUs as well as Google’s Tensor Processing Units (TPUs). We will also discuss the Deployment of the Large Size Deep Learning Models on the Edge devices like NVIDIA Jetson Nano, Google's Edge TPU(Coral).

    Keywords: Graph Optimization, Tensor Fusion, Kernel Auto Tuning, Pruning, Weight sharing, quantization, low-rank approximations, binary networks, ternary networks, Winograd transformations, data parallelism, model parallelism, mixed precision, FP16, FP32, model distillation, Dense-Sparse-Dense training, NVIDIA Volta, Tensor Core, Google TPU.

  • Liked Niraj Kale
    keyboard_arrow_down

    Niraj Kale - Quantum Neural Network

    Niraj Kale
    Niraj Kale
    AI Researcher
    CellStrat
    schedule 3 months ago
    Sold Out!
    20 Mins
    Talk
    Beginner

    Quantum computing has surged in the news and the new breakthroughs put it in a spotlight. Quantum computing can greatly enhance the ML/DL landscape. The new innovation quantum neural networks can greatly accelerate the training and inference of neural networks.

    In this presentation we will see different architectures of QNN. QNN can be build using variational circuits.

    The quantum variational circuits can be used as neural networks. The different architectures in quantum neural network are explored in this presentation. What are the advantages of QNN over traditional ANN. A simple image classification problem using QNN is demonstrated.

  • Liked Rajesh Sampathkumar
    keyboard_arrow_down

    Rajesh Sampathkumar - Defence Against the Dark Arts: Taking Deep Neural Networks from Confusion to Clarity

    20 Mins
    Talk
    Advanced

    Deep Neural Networks are being used in production scale systems for computer vision, audio/video classification and processing, and in many other rich-data centric situations. However, at their core, neural networks are found to be susceptible to noisy, so-called adversarial input, which can potentially enable them to be hacked, or otherwise attacked. How do we understand and quantify the robustness of neural networks to such input? Are there best practices and methods that enable us to understand and accommodate these kinds of attacks on neural networks?

    This talk addresses this specific topic, starting from some of the fundamentals, while exploring adversarial examples, their generation and how they can impact neural network efficacy. We then see how real world attack patterns are related to these adversarial examples, and evaluate some of the scenarios that may arise, specifically in a telecommunications network context. We then discuss some general ideas around defence against such adversarial examples. Additionally, we may also discuss elements of explainability and interpretability as relevant to adversarial attacks on neural networks, and practical considerations with respect to implementation of these techniques and best practices. Relevant research or resources on adversarial attacks and how they can be addressed for deep learning models may also be discussed if time permits.