Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner

Spectacular progress in the information processing sciences (machine learning, wearable sensors) promises to revolutionize the study of cognitive development. Here, we analyse the conditions under which 'reverse engineering' language development, i.e., building an effective system that mimics infant's achievements, can contribute to our scientific understanding of early language development. We argue that, on the computational side, it is important to move from toy problems to the full complexity of the learning situation, and take as input as faithful reconstructions of the sensory signals available to infants as possible. On the data side, accessible but privacy-preserving repositories of home data have to be setup. On the psycholinguistic side, specific tests have to be constructed to benchmark humans and machines at different linguistic levels. We discuss the feasibility of this approach and present an overview of current results.

• Publication year

  2016

• Venue

  Cognition

• Publication date

  2016-07-29

• Fields of study

  Medicine, Linguistics, Computer Science

• Identifiers
  DOI 10.1016/j.cognition.2017.11.008arXiv 1607.08723PMID 29324240
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• The Emergence of the Child as Grammarian

  2020cited by this paper
• The Structural Sources of Verb Meanings

  2020cited by this paper
• Child-Directed Speech Is Infrequent in a Forager-Farmer Population: A Time Allocation Study.

  2019cited by this paper
• The Faculty

  2018cited by this paper
• Triggers

  2018cited by this paper
• Building Machines that Learn and Think Like People

  2018cited by this paper
• A fast, invariant representation for human action in the visual system.

  2018cited by this paper
• Video can make behavioural science more reproducible

  2017cited by this paper
• Neuroscience-Inspired Artificial Intelligence.

  2017cited by this paper
• Grammaticality, Acceptability, and Probability: A Probabilistic View of Linguistic Knowledge

  2017cited by this paper
• Language, Cognition, and Computational Models

  2017cited by this paper
• Evaluating Language Acquisition Models: A Utility-Based Look at Bayesian Segmentation

  2017cited by this paper
• English Conversational Telephone Speech Recognition by Humans and Machines

  2017influential reference
• Learning Word-Like Units from Joint Audio-Visual Analysis

  2017cited by this paper
• A Collaborative Approach to Infant Research: Promoting Reproducibility, Best Practices, and Theory-Building.

  2017cited by this paper
• Relating Unsupervised Word Segmentation to Reported Vocabulary Acquisition

  2017cited by this paper
• Human Learning in Atari

  2017cited by this paper
• Bootstrapping language acquisition.

  2017cited by this paper
• Modeling Phonetic Category Learning from Natural Acoustic Data

  2017cited by this paper
• The zero resource speech challenge 2017

  2017cited by this paper
• Are words easier to learn from infant- than adult-directed speech? A quantitative corpus-based investigation

  2017cited by this paper
• Visually Grounded Meaning Representations

  2017cited by this paper
• Variational Inference for Acoustic Unit Discovery

  2016cited by this paper
• Deep Neural Networks predict Hierarchical Spatio-temporal Cortical Dynamics of Human Visual Object Recognition

  2016cited by this paper
• Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t.

  2016cited by this paper
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

  2016cited by this paper
• Achieving Human Parity in Conversational Speech Recognition

  2016cited by this paper
• Temporally Coherent 4D Reconstruction of Complex Dynamic Scenes

  2016cited by this paper
• Learning a Deep Model for Human Action Recognition from Novel Viewpoints

  2016cited by this paper
• Quantificational features in distributional word representations

  2016cited by this paper
• Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

  2016cited by this paper
• HomeBank: An Online Repository of Daylong Child-Centered Audio Recordings

  2016cited by this paper
• Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

  2016cited by this paper
• The Zero Resource Speech Challenge 2015: Proposed Approaches and Results

  2016cited by this paper
• WaveNet: A Generative Model for Raw Audio

  2016cited by this paper
• Unsupervised Learning of Spoken Language with Visual Context

  2016cited by this paper
• Deep Learning

  2016cited by this paper
• Perceiving referential intent: Dynamics of reference in natural parent-child interactions.

  2016cited by this paper
• Mastering the game of Go with deep neural networks and tree search

  2016cited by this paper
• Noise robustness and stochastic tolerance of OT error-driven ranking algorithms

  2016cited by this paper
• Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

  2016cited by this paper
• Contributions of Head-Mounted Cameras to Studying the Visual Environments of Infants and Young Children

  2015cited by this paper
• Unsupervised Lexicon Discovery from Acoustic Input

  2015cited by this paper
• Motif discovery in infant- and adult-directed speech

  2015cited by this paper
• Exploring Nearest Neighbor Approaches for Image Captioning

  2015cited by this paper
• Computational rationality: A converging paradigm for intelligence in brains, minds, and machines

  2015cited by this paper
• Mothers Speak Less Clearly to Infants Than to Adults: A Comprehensive Test of the Hyperarticulation Hypothesis

  2015cited by this paper
• EmoNets: Multimodal deep learning approaches for emotion recognition in video

  2015cited by this paper
• The zero resource speech challenge 2015

  2015cited by this paper
• A joint model of word segmentation and meaning acquisition through cross-situational learning.

  2015cited by this paper
• Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition

  2015cited by this paper
• Librispeech: An ASR corpus based on public domain audio books

  2015cited by this paper
• Predicting the birth of a spoken word

  2015cited by this paper
• Estimating the reproducibility of psychological science

  2015cited by this paper
• How Nature Meets Nurture: Universal Grammar and Statistical Learning

  2015cited by this paper
• Why the body comes first: effects of experimenter touch on infants' word finding.

  2015cited by this paper
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

  2015cited by this paper
• Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

  2015cited by this paper
• A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling

  2015cited by this paper
• Studying the relationship between physical and language environments of children: Who's speaking to whom and where?

  2015cited by this paper
• Human-level control through deep reinforcement learning

  2015cited by this paper
• Quantitative methods for comparing featural representations

  2015cited by this paper
• VQA: Visual Question Answering

  2015cited by this paper
• Deep Speech: Scaling up end-to-end speech recognition

  2014cited by this paper
• Evolutionary basis for human language. Comment on "Toward a computational framework for cognitive biology: unifying approaches from cognitive neuroscience and comparative cognition" by Tecumseh Fitch.

  2014cited by this paper
• A Survey of Clustering Algorithms for Big Data: Taxonomy and Empirical Analysis

  2014cited by this paper
• A Social Feedback Loop for Speech Development and Its Reduction in Autism

  2014cited by this paper
• Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery

  2014cited by this paper
• Spiking network simulation code for petascale computers

  2014cited by this paper
• The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex

  2014cited by this paper
• An auto-encoder based approach to unsupervised learning of subword units

  2014cited by this paper
• Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition

  2014cited by this paper
• Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors

  2014cited by this paper
• Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems

  2014cited by this paper
• Performance-optimized hierarchical models predict neural responses in higher visual cortex

  2014cited by this paper
• Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics

  2014cited by this paper
• Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

  2014cited by this paper
• Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

  2014cited by this paper
• Incorporating Prosodic Boundaries in Unsupervised Term Discovery

  2014cited by this paper
• Community-Augmented Meta-Analyses

  2014cited by this paper
• A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition

  2014cited by this paper
• A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• (Non)words, (non)words, (non)words: evidence for a protolexicon during the first year of life.

  2013cited by this paper
• Learning Phonemes With a Proto-Lexicon

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Adaptor Grammars for Learning Non-Concatenative Morphology

  2013cited by this paper
• Weak top-down constraints for unsupervised acoustic model training

  2013cited by this paper
• A comparison of informal and formal acceptability judgments using a random sample from Linguistic Inquiry 2001--2010

  2013cited by this paper
• Evaluating speech features with the minimal-pair ABX task: analysis of the classical MFC/PLP pipeline

  2013cited by this paper
• Statistical Representation of Grammaticality Judgements: the Limits of N-Gram Models

  2013cited by this paper
• Cognitive Aspects of Computational Language Acquisition

  2013cited by this paper
• Infant directed speech and the development of speech perception: enhancing development or an unintended consequence?

  2013cited by this paper
• Starting from Scratch in Semantic Role Labeling: Early Indirect Supervision

  2013cited by this paper
• Two-Level Clustering towards Unsupervised Discovery of Acoustic Classes

  2013cited by this paper
• Talking to Children Matters

  2013cited by this paper
• Scalar Implicatures in Child Language: Give Children a Chance

  2012cited by this paper
• Disambiguating Syntactic Triggers

  2012cited by this paper
• A Nonparametric Bayesian Approach to Acoustic Model Discovery

  2012cited by this paper
• Why Science Is Not Necessarily Self-Correcting

  2012cited by this paper

• Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks

  2026influential citation
• The Rise of Foundation Models: Opportunities, Technology, Applications, Challenges, Recent Trends, and Future Directions

  2026cites this paper
• A pipeline for stochastic and controlled generation of realistic language input for simulating infant language acquisition

  2025influential citation
• The Computational Evolution of Cognitive Architectures

  2025cites this paper
• Evaluating the cognitive reality of Spanish irregular morphomic patterns: Humans vs. Transformers

  2025cites this paper
• The Missing Half of Language Learning in Current Developmental Language Models: Exogenous and Endogenous Linguistic Input

  2025cites this paper
• Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?

  2025cites this paper
• Unsupervised lexicon learning from speech is limited by representations rather than clustering

  2025cites this paper
• The intelligibility of consonants in American English infant-directed speech.

  2025cites this paper
• Embodied AI Agents: Modeling the World

  2025cites this paper
• Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier

  2025cites this paper
• Batch-wise Convergent Pre-training: Step-by-Step Learning Inspired by Child Language Development

  2025cites this paper
• Scaling and context steer LLMs along the same computational path as the human brain

  2025cites this paper
• Emergence of Language in the Developing Brain

  2025cites this paper
• Linguists should learn to love speech-based deep learning models

  2025cites this paper
• SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation

  2025cites this paper
• Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora

  2025cites this paper
• Unveiling the multifaceted concept of cognitive security: Trends, perspectives, and future challenges

  2025cites this paper
• Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning

  2025cites this paper
• What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training

  2025cites this paper
• From data to discovery: Technology propels speech-language research and theory-building in developmental science

  2025cites this paper
• BabyLM's First Words: Word Segmentation as a Phonological Probing Task

  2025cites this paper
• Informational embodiment: Computational role of information structure in codes and robots.

  2025cites this paper
• Modelling Child Learning and Parsing of Long-range Syntactic Dependencies

  2025cites this paper
• Do Construction Distributions Shape Formal Language Learning In German BabyLMs?

  2025cites this paper
• Modeling How Suffixes Are Learned in Infancy

  2025cites this paper
• A Distributional Perspective on Word Learning in Neural Language Models

  2025cites this paper
• Simulating Early Phonetic and Word Learning Without Linguistic Categories.

  2025cites this paper
• Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition

  2025cites this paper
• Replication and Information Extraction in a Minimal Agent-Environment Model

  2025cites this paper
• Computational Modeling of the Segmentation of Sentence Stimuli From an Infant Word-Finding Study

  2024cites this paper
• Introduction au numéro spécial sur l’explicabilité des modèles de TAL [Introduction to the special issue on the explainability of NLP models]

  2024cites this paper
• Artificial Intelligence in Language Acquisition: A Balancing Act of Potential and Challenges

  2024cites this paper
• Simulating prenatal language exposure in computational models: An exploration study.

  2024cites this paper
• From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes

  2024cites this paper
• Characterizing English Preposing in PP constructions

  2024cites this paper
• Language Learning, Representation, and Processing in Humans and Machines: Introduction to the Special Issue

  2024cites this paper
• Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming

  2024cites this paper
• Gender and Language Identification in Multilingual Models of Speech: Exploring the Genericity and Robustness of Speech Representations

  2024cites this paper
• Spoken-Term Discovery using Discrete Speech Units

  2024cites this paper
• Informational Embodiment: Computational role of information structure in codes and robots

  2024cites this paper
• No Such Thing as a General Learner: Language models and their dual optimization

  2024cites this paper
• Generating novel experimental hypotheses from language models: A case study on cross-dative generalization

  2024cites this paper
• Investigating Critical Period Effects in Language Acquisition through Neural Language Models

  2024cites this paper
• Unsupervised modeling of vowel harmony using WaveGAN

  2024cites this paper
• A model of early word acquisition based on realistic-scale audiovisual naming events

  2024cites this paper
• MacBehaviour: An R package for behavioural experimentation on large language models

  2024cites this paper
• Age-Dependent Analysis and Stochastic Generation of Child-Directed Speech

  2024cites this paper
• Assessing LLMs in Malicious Code Deobfuscation of Real-world Malware Campaigns

  2024cites this paper
• From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency

  2024cites this paper
• Infant neuroscience: how to measure brain activity in the youngest minds.

  2024cites this paper
• Modeling early phonetic acquisition from child-centered audio data.

  2024cites this paper
• Grounded language acquisition through the eyes and ears of a single child

  2024cites this paper
• Revisiting speech segmentation and lexicon learning with better features

  2024cites this paper
• Communicative Feedback in language acquisition

  2023influential citation
• Realistic and broad-scope learning simulations: first results and challenges

  2023influential citation
• CogMemLM: Human-Like Memory Mechanisms Improve Performance and Cognitive Plausibility of LLMs

  2023cites this paper
• Pre-training LLMs using human-like development data corpus

  2023cites this paper
• Artificial intelligence-based language learning: illuminating the impact on speaking skills and self-regulation in Chinese EFL context

  2023cites this paper
• Using an Egocentric Human Simulation Paradigm to quantify referential and semantic ambiguity in early word learning

  2023cites this paper
• Investigating the Existence of "Secret Language" in Language Models

  2023cites this paper
• Audio-Visual Neural Syntax Acquisition

  2023cites this paper
• Artificial Neural Network Language Models Predict Human Brain Responses to Language Even After a Developmentally Realistic Amount of Training

  2023cites this paper
• Compositional Learning of Visually-Grounded Concepts Using Reinforcement

  2023cites this paper
• Bridging the data gap between children and large language models.

  2023cites this paper
• The Effect Of Using The Flipped Classroom Learning Model Using Video Interactive Media On Learning Outcomes

  2023cites this paper
• Memory Network-Based End-To-End Neural ES-KMeans for Improved Word Segmentation

  2023cites this paper
• Unsupervised Learning of Discrete Latent Representations with Data-Adaptive Dimensionality from Continuous Speech Streams

  2023cites this paper
• Why can big.bi be changed to bi.gbi? A mathematical model of syllabification and articulatory synthesis

  2023cites this paper
• Introducing Meta-analysis in the Evaluation of Computational Models of Infant Language Development

  2023cites this paper
• Finding Structure in One Child's Linguistic Experience.

  2023influential citation
• Language acquisition: do children and language models follow similar learning stages?

  2023cites this paper
• On “Scientific Debt” in NLP: A Case for More Rigour in Language Model Pre-Training Research

  2023cites this paper
• Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder

  2023cites this paper
• On the Nature of Discrete Speech Representations in Multilingual Self-supervised Models

  2023cites this paper
• A framework for the emergence and analysis of language in social learning agents

  2023cites this paper
• The Construction of Reality in an AI: A Review

  2023cites this paper
• Does Vision Accelerate Hierarchical Generalization of Neural Language Learners?

  2023cites this paper
• Call for Papers - The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus

  2023cites this paper
• Does Vision Accelerate Hierarchical Generalization in Neural Language Learners?

  2023cites this paper
• Simulating vocal learning of spoken language: Beyond imitation

  2023cites this paper
• BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models

  2023cites this paper
• Artificial neural network language models align neurally and behaviorally with humans even after a developmentally realistic amount of training

  2022cites this paper
• Dynamic manifold Boltzmann optimization based on self-supervised learning for human motion estimation

  2022cites this paper
• Infants’ Learning of Speech Sounds and Word-Forms

  2022cites this paper
• Word Discovery in Visually Grounded, Self-Supervised Speech Models

  2022cites this paper
• A systematic review suggests marked differences in the prevalence of infant-directed vocalization across groups of populations.

  2022cites this paper
• Unsupervised Word Segmentation using K Nearest Neighbors

  2022cites this paper
• Context Limitations Make Neural Language Models More Human-Like

  2022cites this paper
• Toward a realistic model of speech processing in the brain with self-supervised learning

  2022cites this paper
• How adults understand what young children say

  2022cites this paper
• A Study of Artificial Intelligence-Based Poster Layout Design in Visual Communication

  2022cites this paper
• Automatic Spoken Language Acquisition Based on Observation and Dialogue

  2022cites this paper
• Inferring the nature of linguistic computations in the brain

  2022cites this paper
• What Artificial Neural Networks Can Tell Us About Human Language Acquisition

  2022cites this paper
• Emergent Communication at Scale

  2022cites this paper
• Synthesizing theories of human language with Bayesian program induction

  2022cites this paper
• Self-Supervised Language Learning From Raw Audio: Lessons From the Zero Resource Speech Challenge

  2022cites this paper
• Semi-supervised Acoustic and Language Modeling for Hindi ASR

  2022cites this paper
• Evaluating unsupervised word segmentation in adults: a meta-analysis

  2022cites this paper